Merge branch 'master' of https://github.com/spacy-io/spaCy

.gitignore

@@ -0,0 +1,103 @@
+# Vim
+*.swp
+*.sw*
+Profile.prof
+tmp/
+.dev
+.denv
+.pypyenv
+.eggs
+*.tgz
+.sass-cache
+
+MANIFEST
+
+corpora/
+models/
+examples/
+keys/
+
+spacy/syntax/*.cpp
+spacy/syntax/*.html
+spacy/en/*.cpp
+spacy/tokens/*.cpp
+spacy/serialize/*.cpp
+spacy/en/data/*
+spacy/*.cpp
+spacy/ner/*.cpp
+spacy/orthography/*.cpp
+ext/murmurhash.cpp
+ext/sparsehash.cpp
+
+data/en/pos
+data/en/ner
+data/en/lexemes
+data/en/strings
+
+_build/
+.env/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+bin/
+build/
+develop-eggs/
+dist/
+eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.cache
+nosetests.xml
+coverage.xml
+
+# Website
+website/www/
+website/demos/displacy/
+website/demos/sense2vec/
+
+# Translations
+*.mo
+
+# Mr Developer
+.mr.developer.cfg
+.project
+.pydevproject
+
+# Rope
+.ropeproject
+
+# Django stuff:
+*.log
+*.pot
+
+# Windows local helper files
+*.bat
+
+# Mac OS X
+*.DS_Store
+
+# Komodo project files
+*.komodoproject

.travis.yml

@@ -0,0 +1,30 @@
+language: python
+
+sudo: required
+dist: precise
+group: edge
+
+python:
+   - "2.7"
+   - "3.4"
+
+os:
+  - linux
+
+install:
+  - "pip install -r requirements.txt"
+  - "pip install -e ."
+  - "mkdir -p corpora/en"
+  - "cd corpora/en"
+  - "wget --no-check-certificate http://wordnetcode.princeton.edu/3.0/WordNet-3.0.tar.gz"
+  - "tar -xzf WordNet-3.0.tar.gz"
+  - "mv WordNet-3.0 wordnet"
+  - "cd ../../"
+  - "python bin/init_model.py en lang_data/ corpora/ data"
+  - "cp package.json data"
+  - "sputnik build data en_default.sputnik"
+  - "sputnik --name spacy install en_default.sputnik"
+
+script:
+  - "pip install pytest"
+  - "python -m pytest spacy"

LICENSE

@@ -0,0 +1,22 @@
+The MIT License (MIT)
+
+Copyright (C) 2015 Matthew Honnibal
+              2016 spaCy GmbH
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

MANIFEST.in

@@ -0,0 +1,4 @@
+recursive-include include *.h
+include buildbot.json
+include LICENSE
+include README.rst

README.rst

@@ -0,0 +1,111 @@
+.. image:: https://travis-ci.org/spacy-io/spaCy.svg?branch=master
+    :target: https://travis-ci.org/spacy-io/spaCy
+
+==============================
+spaCy: Industrial-strength NLP
+==============================
+
+spaCy is a library for advanced natural language processing in Python and Cython.
+
+Documentation and details: https://spacy.io/
+
+spaCy is built on the very latest research, but it isn't researchware.  It was
+designed from day 1 to be used in real products. It's commercial open-source
+software, released under the MIT license.
+
+Features
+--------
+
+* Labelled dependency parsing (91.8% accuracy on OntoNotes 5)
+
+* Named entity recognition (82.6% accuracy on OntoNotes 5)
+
+* Part-of-speech tagging (97.1% accuracy on OntoNotes 5)
+
+* Easy to use word vectors
+
+* All strings mapped to integer IDs
+
+* Export to numpy data arrays
+
+* Alignment maintained to original string, ensuring easy mark up calculation
+
+* Range of easy-to-use orthographic features.
+
+* No pre-processing required. spaCy takes raw text as input, warts and newlines and all.
+
+Top Peformance
+--------------
+
+* Fastest in the world: <50ms per document.  No faster system has ever been
+  announced.
+
+* Accuracy within 1% of the current state of the art on all tasks performed
+  (parsing, named entity recognition, part-of-speech tagging).  The only more
+  accurate systems are an order of magnitude slower or more.
+
+Supports
+--------
+
+* CPython 2.6, 2.7, 3.3, 3.4, 3.5 (only 64 bit)
+* OSX
+* Linux
+* Windows (Cygwin, MinGW, Visual Studio)
+
+
+2016-05-0 0.101.0: Fixed German model
+-------------------------------------
+
+* Fixed bug that prevented German parses from being deprojectivised.
+
+* Bug fixes to sentence boundary detection.
+
+* Add rich comparison methods to the Lexeme class.
+
+* Add missing Doc.has_vector and Span.has_vector properties.
+
+* Add missing Span.sent property.
+
+
+2016-05-05 v0.100.7: German!
+----------------------------
+
+spaCy finally supports another language, in addition to English. We're lucky to have Wolfgang Seeker on the team, and the new German model is just the beginning.
+Now that there are multiple languages, you should consider loading spaCy via the load() function. This function also makes it easier to load extra word vector data for English:
+
+.. code:: python
+
+    import spacy
+    en_nlp = spacy.load('en', vectors='en_glove_cc_300_1m_vectors')
+    de_nlp = spacy.load('de')
+    
+To support use of the load function, there are also two new helper functions: spacy.get_lang_class and spacy.set_lang_class.
+Once the German model is loaded, you can use it just like the English model:
+
+.. code:: python
+
+    doc = nlp(u'''Wikipedia ist ein Projekt zum Aufbau einer Enzyklopädie aus freien Inhalten, zu dem du mit deinem Wissen beitragen kannst. Seit Mai 2001 sind 1.936.257 Artikel in deutscher Sprache entstanden.''')
+    
+    for sent in doc.sents:
+        print(sent.root.text, sent.root.n_lefts, sent.root.n_rights)
+    
+    # (u'ist', 1, 2)
+    # (u'sind', 1, 3)
+    
+The German model provides tokenization, POS tagging, sentence boundary detection, syntactic dependency parsing, recognition of organisation, location and person entities, and word vector representations trained on a mix of open subtitles and Wikipedia data. It doesn't yet provide lemmatisation or morphological analysis, and it doesn't yet recognise numeric entities such as numbers and dates.
+
+Bugfixes
+--------
+
+* spaCy < 0.100.7 had a bug in the semantics of the Token.__str__ and Token.__unicode__ built-ins: they included a trailing space.
+* Improve handling of "infixed" hyphens. Previously the tokenizer struggled with multiple hyphens, such as "well-to-do".
+
+* Improve handling of periods after mixed-case tokens
+
+* Improve lemmatization for English special-case tokens
+
+* Fix bug that allowed spaces to be treated as heads in the syntactic parse
+
+* Fix bug that led to inconsistent sentence boundaries before and after serialisation.
+
+* Fix bug from deserialising untagged documents.

bin/cythonize.py

@@ -0,0 +1,156 @@
+#!/usr/bin/env python
+""" cythonize.py
+
+Cythonize pyx files into C++ files as needed.
+
+Usage: cythonize.py [root]
+
+Checks pyx files to see if they have been changed relative to their
+corresponding C++ files. If they have, then runs cython on these files to
+recreate the C++ files.
+
+Additionally, checks pxd files and setup.py if they have been changed. If
+they have, rebuilds everything.
+
+Change detection based on file hashes stored in JSON format.
+
+For now, this script should be run by developers when changing Cython files
+and the resulting C++ files checked in, so that end-users (and Python-only
+developers) do not get the Cython dependencies.
+
+Based upon:
+
+https://raw.github.com/dagss/private-scipy-refactor/cythonize/cythonize.py
+https://raw.githubusercontent.com/numpy/numpy/master/tools/cythonize.py
+
+Note: this script does not check any of the dependent C++ libraries.
+"""
+from __future__ import print_function
+
+import os
+import sys
+import json
+import hashlib
+import subprocess
+import argparse
+
+
+HASH_FILE = 'cythonize.json'
+
+
+def process_pyx(fromfile, tofile):
+    print('Processing %s' % fromfile)
+    try:
+        from Cython.Compiler.Version import version as cython_version
+        from distutils.version import LooseVersion
+        if LooseVersion(cython_version) < LooseVersion('0.19'):
+            raise Exception('Require Cython >= 0.19')
+
+    except ImportError:
+        pass
+
+    flags = ['--fast-fail']
+    if tofile.endswith('.cpp'):
+        flags += ['--cplus']
+
+    try:
+        try:
+            r = subprocess.call(['cython'] + flags + ['-o', tofile, fromfile])
+            if r != 0:
+                raise Exception('Cython failed')
+        except OSError:
+            # There are ways of installing Cython that don't result in a cython
+            # executable on the path, see gh-2397.
+            r = subprocess.call([sys.executable, '-c',
+                                'import sys; from Cython.Compiler.Main import '
+                                'setuptools_main as main; sys.exit(main())'] + flags +
+                                ['-o', tofile, fromfile])
+            if r != 0:
+                raise Exception('Cython failed')
+    except OSError:
+        raise OSError('Cython needs to be installed')
+
+
+def preserve_cwd(path, func, *args):
+    orig_cwd = os.getcwd()
+    try:
+        os.chdir(path)
+        func(*args)
+    finally:
+        os.chdir(orig_cwd)
+
+
+def load_hashes(filename):
+    try:
+        return json.load(open(filename))
+    except (ValueError, IOError):
+        return {}
+
+
+def save_hashes(hash_db, filename):
+    with open(filename, 'w') as f:
+        f.write(json.dumps(hash_db))
+
+
+def get_hash(path):
+    return hashlib.md5(open(path, 'rb').read()).hexdigest()
+
+
+def hash_changed(base, path, db):
+    full_path = os.path.normpath(os.path.join(base, path))
+    return not get_hash(full_path) == db.get(full_path)
+
+
+def hash_add(base, path, db):
+    full_path = os.path.normpath(os.path.join(base, path))
+    db[full_path] = get_hash(full_path)
+
+
+def process(base, filename, db):
+    root, ext = os.path.splitext(filename)
+    if ext in ['.pyx', '.cpp']:
+        if hash_changed(base, filename, db) or not os.path.isfile(os.path.join(base, root + '.cpp')):
+            preserve_cwd(base, process_pyx, root + '.pyx', root + '.cpp')
+            hash_add(base, root + '.cpp', db)
+            hash_add(base, root + '.pyx', db)
+
+
+def check_changes(root, db):
+    res = False
+    new_db = {}
+
+    setup_filename = 'setup.py'
+    hash_add('.', setup_filename, new_db)
+    if hash_changed('.', setup_filename, db):
+        res = True
+
+    for base, _, files in os.walk(root):
+        for filename in files:
+            if filename.endswith('.pxd'):
+                hash_add(base, filename, new_db)
+                if hash_changed(base, filename, db):
+                    res = True
+
+    if res:
+        db.clear()
+        db.update(new_db)
+    return res
+
+
+def run(root):
+    db = load_hashes(HASH_FILE)
+
+    try:
+        check_changes(root, db)
+        for base, _, files in os.walk(root):
+            for filename in files:
+                process(base, filename, db)
+    finally:
+        save_hashes(db, HASH_FILE)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description='Cythonize pyx files into C++ files as needed')
+    parser.add_argument('root', help='root directory')
+    args = parser.parse_args()
+    run(args.root)

bin/get_freqs.py

@@ -0,0 +1,93 @@
+#!/usr/bin/env python
+
+from __future__ import unicode_literals, print_function
+
+import plac
+import joblib
+from os import path
+import os
+import bz2
+import ujson
+from preshed.counter import PreshCounter
+from joblib import Parallel, delayed
+import io
+
+from spacy.en import English
+from spacy.strings import StringStore
+from spacy.attrs import ORTH
+from spacy.tokenizer import Tokenizer
+from spacy.vocab import Vocab
+
+
+def iter_comments(loc):
+    with bz2.BZ2File(loc) as file_:
+        for line in file_:
+            yield ujson.loads(line)
+
+
+def count_freqs(input_loc, output_loc):
+    print(output_loc)
+    vocab = English.default_vocab(get_lex_attr=None)
+    tokenizer = Tokenizer.from_dir(vocab,
+                    path.join(English.default_data_dir(), 'tokenizer'))
+
+    counts = PreshCounter()
+    for json_comment in iter_comments(input_loc):
+        doc = tokenizer(json_comment['body'])
+        doc.count_by(ORTH, counts=counts)
+
+    with io.open(output_loc, 'w', 'utf8') as file_:
+        for orth, freq in counts:
+            string = tokenizer.vocab.strings[orth]
+            if not string.isspace():
+                file_.write('%d\t%s\n' % (freq, string))
+
+
+def parallelize(func, iterator, n_jobs):
+    Parallel(n_jobs=n_jobs)(delayed(func)(*item) for item in iterator)
+
+
+def merge_counts(locs, out_loc):
+    string_map = StringStore()
+    counts = PreshCounter()
+    for loc in locs:
+        with io.open(loc, 'r', encoding='utf8') as file_:
+            for line in file_:
+                freq, word = line.strip().split('\t', 1)
+                orth = string_map[word]
+                counts.inc(orth, int(freq))
+    with io.open(out_loc, 'w', encoding='utf8') as file_:
+        for orth, count in counts:
+            string = string_map[orth]
+            file_.write('%d\t%s\n' % (count, string))
+
+
+@plac.annotations(
+    input_loc=("Location of input file list"),
+    freqs_dir=("Directory for frequency files"),
+    output_loc=("Location for output file"),
+    n_jobs=("Number of workers", "option", "n", int),
+    skip_existing=("Skip inputs where an output file exists", "flag", "s", bool),
+)
+def main(input_loc, freqs_dir, output_loc, n_jobs=2, skip_existing=False):
+    tasks = []
+    outputs = []
+    for input_path in open(input_loc):
+        input_path = input_path.strip()
+        if not input_path:
+            continue
+        filename = input_path.split('/')[-1]
+        output_path = path.join(freqs_dir, filename.replace('bz2', 'freq'))
+        outputs.append(output_path)
+        if not path.exists(output_path) or not skip_existing:
+            tasks.append((input_path, output_path))
+
+    if tasks:
+        parallelize(count_freqs, tasks, n_jobs)
+
+    print("Merge")
+    merge_counts(outputs, output_loc)
+                
+
+if __name__ == '__main__':
+    plac.call(main)

bin/init_model.py

@@ -0,0 +1,228 @@
+"""Set up a model directory.
+
+Requires:
+
+    lang_data --- Rules for the tokenizer
+        * prefix.txt
+        * suffix.txt
+        * infix.txt
+        * morphs.json
+        * specials.json
+
+    corpora --- Data files
+        * WordNet
+        * words.sgt.prob --- Smoothed unigram probabilities
+        * clusters.txt --- Output of hierarchical clustering, e.g. Brown clusters
+        * vectors.bz2 --- output of something like word2vec, compressed with bzip
+"""
+from __future__ import unicode_literals
+
+from ast import literal_eval
+import math
+import gzip
+import json
+
+import plac
+from pathlib import Path
+
+from shutil import copyfile
+from shutil import copytree
+from collections import defaultdict
+import io
+
+from spacy.vocab import Vocab
+from spacy.vocab import write_binary_vectors
+from spacy.strings import hash_string
+from preshed.counter import PreshCounter
+
+from spacy.parts_of_speech import NOUN, VERB, ADJ
+from spacy.util import get_lang_class
+
+
+try:
+    unicode
+except NameError:
+    unicode = str
+
+
+def setup_tokenizer(lang_data_dir, tok_dir):
+    if not tok_dir.exists():
+        tok_dir.mkdir()
+
+    for filename in ('infix.txt', 'morphs.json', 'prefix.txt', 'specials.json',
+                     'suffix.txt'):
+        src = lang_data_dir / filename
+        dst = tok_dir / filename
+        copyfile(str(src), str(dst))
+
+
+def _read_clusters(loc):
+    if not loc.exists():
+        print("Warning: Clusters file not found")
+        return {}
+    clusters = {}
+    for line in io.open(str(loc), 'r', encoding='utf8'):
+        try:
+            cluster, word, freq = line.split()
+        except ValueError:
+            continue
+        # If the clusterer has only seen the word a few times, its cluster is
+        # unreliable.
+        if int(freq) >= 3:
+            clusters[word] = cluster
+        else:
+            clusters[word] = '0'
+    # Expand clusters with re-casing
+    for word, cluster in list(clusters.items()):
+        if word.lower() not in clusters:
+            clusters[word.lower()] = cluster
+        if word.title() not in clusters:
+            clusters[word.title()] = cluster
+        if word.upper() not in clusters:
+            clusters[word.upper()] = cluster
+    return clusters
+
+
+def _read_probs(loc):
+    if not loc.exists():
+        print("Probabilities file not found. Trying freqs.")
+        return {}, 0.0
+    probs = {}
+    for i, line in enumerate(io.open(str(loc), 'r', encoding='utf8')):
+        prob, word = line.split()
+        prob = float(prob)
+        probs[word] = prob
+    return probs, probs['-OOV-']
+
+
+def _read_freqs(loc, max_length=100, min_doc_freq=5, min_freq=200):
+    if not loc.exists():
+        print("Warning: Frequencies file not found")
+        return {}, 0.0
+    counts = PreshCounter()
+    total = 0
+    if str(loc).endswith('gz'):
+        file_ = gzip.open(str(loc))
+    else:
+        file_ = loc.open()
+    for i, line in enumerate(file_):
+        freq, doc_freq, key = line.rstrip().split('\t', 2)
+        freq = int(freq)
+        counts.inc(i+1, freq)
+        total += freq
+    counts.smooth()
+    log_total = math.log(total)
+    if str(loc).endswith('gz'):
+        file_ = gzip.open(str(loc))
+    else:
+        file_ = loc.open()
+    probs = {}
+    for line in file_:
+        freq, doc_freq, key = line.rstrip().split('\t', 2)
+        doc_freq = int(doc_freq)
+        freq = int(freq)
+        if doc_freq >= min_doc_freq and freq >= min_freq and len(key) < max_length:
+            word = literal_eval(key)
+            smooth_count = counts.smoother(int(freq))
+            probs[word] = math.log(smooth_count) - log_total
+    oov_prob = math.log(counts.smoother(0)) - log_total
+    return probs, oov_prob
+
+
+def _read_senses(loc):
+    lexicon = defaultdict(lambda: defaultdict(list))
+    if not loc.exists():
+        print("Warning: WordNet senses not found")
+        return lexicon
+    sense_names = dict((s, i) for i, s in enumerate(spacy.senses.STRINGS))
+    pos_ids = {'noun': NOUN, 'verb': VERB, 'adjective': ADJ}
+    for line in codecs.open(str(loc), 'r', 'utf8'):
+        sense_strings = line.split()
+        word = sense_strings.pop(0)
+        for sense in sense_strings:
+            pos, sense = sense[3:].split('.')
+            sense_name = '%s_%s' % (pos[0].upper(), sense.lower())
+            if sense_name != 'N_tops':
+                sense_id = sense_names[sense_name]
+                lexicon[word][pos_ids[pos]].append(sense_id)
+    return lexicon
+
+
+def setup_vocab(get_lex_attr, tag_map, src_dir, dst_dir):
+    if not dst_dir.exists():
+        dst_dir.mkdir()
+
+    vectors_src = src_dir / 'vectors.bz2'
+    if vectors_src.exists():
+        write_binary_vectors(str(vectors_src), str(dst_dir / 'vec.bin'))
+    else:
+        print("Warning: Word vectors file not found")
+    vocab = Vocab(get_lex_attr=get_lex_attr, tag_map=tag_map)
+    clusters = _read_clusters(src_dir / 'clusters.txt')
+    probs, oov_prob = _read_probs(src_dir / 'words.sgt.prob')
+    if not probs:
+        probs, oov_prob = _read_freqs(src_dir / 'freqs.txt.gz')
+    if not probs:
+        oov_prob = -20
+    else:
+        oov_prob = min(probs.values())
+    for word in clusters:
+        if word not in probs:
+            probs[word] = oov_prob
+
+    lexicon = []
+    for word, prob in reversed(sorted(list(probs.items()), key=lambda item: item[1])):
+        # First encode the strings into the StringStore. This way, we can map
+        # the orth IDs to frequency ranks
+        orth = vocab.strings[word]
+    # Now actually load the vocab
+    for word, prob in reversed(sorted(list(probs.items()), key=lambda item: item[1])):
+        lexeme = vocab[word]
+        lexeme.prob = prob
+        lexeme.is_oov = False
+        # Decode as a little-endian string, so that we can do & 15 to get
+        # the first 4 bits. See _parse_features.pyx
+        if word in clusters:
+            lexeme.cluster = int(clusters[word][::-1], 2)
+        else:
+            lexeme.cluster = 0
+    vocab.dump(str(dst_dir / 'lexemes.bin'))
+    with (dst_dir / 'strings.json').open('w') as file_:
+        vocab.strings.dump(file_)
+    with (dst_dir / 'oov_prob').open('w') as file_:
+        file_.write('%f' % oov_prob)
+
+
+def main(lang_id, lang_data_dir, corpora_dir, model_dir):
+    model_dir = Path(model_dir)
+    lang_data_dir = Path(lang_data_dir) / lang_id
+    corpora_dir = Path(corpora_dir) / lang_id
+
+    assert corpora_dir.exists()
+    assert lang_data_dir.exists()
+
+    if not model_dir.exists():
+        model_dir.mkdir()
+
+    tag_map = json.load((lang_data_dir / 'tag_map.json').open())
+    setup_tokenizer(lang_data_dir, model_dir / 'tokenizer')
+    setup_vocab(get_lang_class(lang_id).default_lex_attrs(), tag_map, corpora_dir,
+                model_dir / 'vocab')
+
+    if (lang_data_dir / 'gazetteer.json').exists():
+        copyfile(str(lang_data_dir / 'gazetteer.json'),
+                 str(model_dir / 'vocab' / 'gazetteer.json'))
+
+    copyfile(str(lang_data_dir / 'tag_map.json'),
+             str(model_dir / 'vocab' / 'tag_map.json'))
+
+    if (lang_data_dir / 'lemma_rules.json').exists():
+        copyfile(str(lang_data_dir / 'lemma_rules.json'),
+                 str(model_dir / 'vocab' / 'lemma_rules.json'))
+
+    if not (model_dir / 'wordnet').exists() and (corpora_dir / 'wordnet').exists():
+        copytree(str(corpora_dir / 'wordnet' / 'dict'), str(model_dir / 'wordnet'))
+
+
+if __name__ == '__main__':
+    plac.call(main)

bin/munge_ewtb.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python
+from __future__ import unicode_literals
+
+from xml.etree import cElementTree as ElementTree
+import json
+import re
+
+import plac
+from pathlib import Path
+from os import path
+
+
+escaped_tokens = {
+    '-LRB-': '(',
+    '-RRB-': ')',
+    '-LSB-': '[',
+    '-RSB-': ']',
+    '-LCB-': '{',
+    '-RCB-': '}',
+}
+
+def read_parses(parse_loc):
+    offset = 0
+    doc = []
+    for parse in open(str(parse_loc) + '.dep').read().strip().split('\n\n'):
+        parse = _adjust_token_ids(parse, offset)
+        offset += len(parse.split('\n'))
+        doc.append(parse)
+    return doc
+
+def _adjust_token_ids(parse, offset):
+    output = []
+    for line in parse.split('\n'):
+        pieces = line.split()
+        pieces[0] = str(int(pieces[0]) + offset)
+        pieces[5] = str(int(pieces[5]) + offset) if pieces[5] != '0' else '0'
+        output.append('\t'.join(pieces))
+    return '\n'.join(output)
+
+
+def _fmt_doc(filename, paras):
+    return {'id': filename, 'paragraphs': [_fmt_para(*para) for para in paras]}
+
+
+def _fmt_para(raw, sents):
+    return {'raw': raw, 'sentences': [_fmt_sent(sent) for sent in sents]}
+
+
+def _fmt_sent(sent):
+    return {
+        'tokens': [_fmt_token(*t.split()) for t in sent.strip().split('\n')],
+        'brackets': []}
+
+
+def _fmt_token(id_, word, hyph, pos, ner, head, dep, blank1, blank2, blank3):
+    head = int(head) - 1
+    id_ = int(id_) - 1
+    head = (head - id_) if head != -1 else 0
+    return {'id': id_, 'orth': word, 'tag': pos, 'dep': dep, 'head': head}
+
+
+tags_re = re.compile(r'<[\w\?/][^>]+>')
+def main(out_dir, ewtb_dir='/usr/local/data/eng_web_tbk'):
+    ewtb_dir = Path(ewtb_dir)
+    out_dir = Path(out_dir)
+    if not out_dir.exists():
+        out_dir.mkdir()
+    for genre_dir in ewtb_dir.joinpath('data').iterdir():
+        #if 'answers' in str(genre_dir): continue
+        parse_dir = genre_dir.joinpath('penntree')
+        docs = []
+        for source_loc in genre_dir.joinpath('source').joinpath('source_original').iterdir():
+            filename = source_loc.parts[-1].replace('.sgm.sgm', '')
+            filename = filename.replace('.xml', '')
+            filename = filename.replace('.txt', '')
+            parse_loc = parse_dir.joinpath(filename + '.xml.tree')
+            parses = read_parses(parse_loc)
+            source = source_loc.open().read().strip()
+            if 'answers' in str(genre_dir):
+                source = tags_re.sub('', source).strip()
+            docs.append(_fmt_doc(filename, [[source, parses]]))
+
+        out_loc = out_dir.joinpath(genre_dir.parts[-1] + '.json')
+        with open(str(out_loc), 'w') as out_file:
+            out_file.write(json.dumps(docs, indent=4))
+
+
+if __name__ == '__main__':
+    plac.call(main)

bin/ner_tag.py

@@ -0,0 +1,32 @@
+import io
+import plac
+
+from spacy.en import English
+
+
+def main(text_loc):
+    with io.open(text_loc, 'r', encoding='utf8') as file_:
+        text = file_.read()
+    NLU = English()
+    for paragraph in text.split('\n\n'):
+        tokens = NLU(paragraph)
+
+        ent_starts = {}
+        ent_ends = {}
+        for span in tokens.ents:
+            ent_starts[span.start] = span.label_
+            ent_ends[span.end] = span.label_
+
+        output = []
+        for token in tokens:
+            if token.i in ent_starts:
+                output.append('<%s>' % ent_starts[token.i])
+            output.append(token.orth_)
+            if (token.i+1) in ent_ends:
+                output.append('</%s>' % ent_ends[token.i+1])
+        output.append('\n\n')
+    print ' '.join(output)
+
+
+if __name__ == '__main__':
+    plac.call(main)

bin/parser/conll_parse.py

@@ -0,0 +1,130 @@
+#!/usr/bin/env python
+from __future__ import division
+from __future__ import unicode_literals
+
+import os
+from os import path
+import shutil
+import codecs
+import random
+import time
+import gzip
+
+import plac
+import cProfile
+import pstats
+
+import spacy.util
+from spacy.en import English
+from spacy.en.pos import POS_TEMPLATES, POS_TAGS, setup_model_dir
+
+from spacy.syntax.parser import GreedyParser
+from spacy.syntax.parser import OracleError
+from spacy.syntax.util import Config
+
+
+def is_punct_label(label):
+    return label == 'P' or label.lower() == 'punct'
+
+
+def read_gold(file_):
+    """Read a standard CoNLL/MALT-style format"""
+    sents = []
+    for sent_str in file_.read().strip().split('\n\n'):
+        ids = []
+        words = []
+        heads = []
+        labels = []
+        tags = []
+        for i, line in enumerate(sent_str.split('\n')):
+            id_, word, pos_string, head_idx, label = _parse_line(line)
+            words.append(word)
+            if head_idx == -1:
+                head_idx = i
+            ids.append(id_)
+            heads.append(head_idx)
+            labels.append(label)
+            tags.append(pos_string)
+        text = ' '.join(words)
+        sents.append((text, [words], ids, words, tags, heads, labels))
+    return sents
+
+
+def _parse_line(line):
+    pieces = line.split()
+    id_ = int(pieces[0])
+    word = pieces[1]
+    pos = pieces[3]
+    head_idx = int(pieces[6])
+    label = pieces[7]
+    return id_, word, pos, head_idx, label
+
+        
+def iter_data(paragraphs, tokenizer, gold_preproc=False):
+    for raw, tokenized, ids, words, tags, heads, labels in paragraphs:
+        assert len(words) == len(heads)
+        for words in tokenized:
+            sent_ids = ids[:len(words)]
+            sent_tags = tags[:len(words)]
+            sent_heads = heads[:len(words)]
+            sent_labels = labels[:len(words)]
+            sent_heads = _map_indices_to_tokens(sent_ids, sent_heads)
+            tokens = tokenizer.tokens_from_list(words)
+            yield tokens, sent_tags, sent_heads, sent_labels
+            ids = ids[len(words):]
+            tags = tags[len(words):]
+            heads = heads[len(words):]
+            labels = labels[len(words):]
+
+
+def _map_indices_to_tokens(ids, heads):
+    mapped = []
+    for head in heads:
+        if head not in ids:
+            mapped.append(None)
+        else:
+            mapped.append(ids.index(head))
+    return mapped
+
+
+
+def evaluate(Language, dev_loc, model_dir):
+    global loss
+    nlp = Language()
+    n_corr = 0
+    pos_corr = 0
+    n_tokens = 0
+    total = 0
+    skipped = 0
+    loss = 0
+    with codecs.open(dev_loc, 'r', 'utf8') as file_:
+        paragraphs = read_gold(file_)
+    for tokens, tag_strs, heads, labels in iter_data(paragraphs, nlp.tokenizer):
+        assert len(tokens) == len(labels)
+        nlp.tagger.tag_from_strings(tokens, tag_strs)
+        nlp.parser(tokens)
+        for i, token in enumerate(tokens):
+            try:
+                pos_corr += token.tag_ == tag_strs[i]
+            except:
+                print i, token.orth_, token.tag
+                raise
+            n_tokens += 1
+            if heads[i] is None:
+                skipped += 1
+                continue
+            if is_punct_label(labels[i]):
+                continue
+            n_corr += token.head.i == heads[i]
+            total += 1
+    print loss, skipped, (loss+skipped + total)
+    print pos_corr / n_tokens
+    return float(n_corr) / (total + loss)
+
+
+def main(dev_loc, model_dir):
+    print evaluate(English, dev_loc, model_dir)
+    
+
+if __name__ == '__main__':
+    plac.call(main)

bin/parser/conll_train.py

@@ -0,0 +1,157 @@
+#!/usr/bin/env python
+from __future__ import division
+from __future__ import unicode_literals
+
+import os
+from os import path
+import shutil
+import io
+import random
+import time
+import gzip
+
+import plac
+import cProfile
+import pstats
+
+import spacy.util
+from spacy.en import English
+from spacy.gold import GoldParse
+
+from spacy.syntax.util import Config
+from spacy.syntax.arc_eager import ArcEager
+from spacy.syntax.parser import Parser
+from spacy.scorer import Scorer
+from spacy.tagger import Tagger
+
+# Last updated for spaCy v0.97
+
+
+def read_conll(file_):
+    """Read a standard CoNLL/MALT-style format"""
+    sents = []
+    for sent_str in file_.read().strip().split('\n\n'):
+        ids = []
+        words = []
+        heads = []
+        labels = []
+        tags = []
+        for i, line in enumerate(sent_str.split('\n')):
+            word, pos_string, head_idx, label = _parse_line(line)
+            words.append(word)
+            if head_idx < 0:
+                head_idx = i
+            ids.append(i)
+            heads.append(head_idx)
+            labels.append(label)
+            tags.append(pos_string)
+        text = ' '.join(words)
+        annot = (ids, words, tags, heads, labels, ['O'] * len(ids))
+        sents.append((None, [(annot, [])]))
+    return sents
+
+
+def _parse_line(line):
+    pieces = line.split()
+    if len(pieces) == 4:
+        word, pos, head_idx, label = pieces
+        head_idx = int(head_idx)
+    elif len(pieces) == 15:
+        id_ = int(pieces[0].split('_')[-1])
+        word = pieces[1]
+        pos = pieces[4]
+        head_idx = int(pieces[8])-1
+        label = pieces[10]
+    else:
+        id_ = int(pieces[0].split('_')[-1])
+        word = pieces[1]
+        pos = pieces[4]
+        head_idx = int(pieces[6])-1
+        label = pieces[7]
+    if head_idx == 0:
+        label = 'ROOT'
+    return word, pos, head_idx, label
+
+        
+def score_model(scorer, nlp, raw_text, annot_tuples, verbose=False):
+    tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])
+    nlp.tagger(tokens)
+    nlp.parser(tokens)
+    gold = GoldParse(tokens, annot_tuples, make_projective=False)
+    scorer.score(tokens, gold, verbose=verbose, punct_labels=('--', 'p', 'punct'))
+
+
+def train(Language, gold_tuples, model_dir, n_iter=15, feat_set=u'basic', seed=0,
+          gold_preproc=False, force_gold=False):
+    dep_model_dir = path.join(model_dir, 'deps')
+    pos_model_dir = path.join(model_dir, 'pos')
+    if path.exists(dep_model_dir):
+        shutil.rmtree(dep_model_dir)
+    if path.exists(pos_model_dir):
+        shutil.rmtree(pos_model_dir)
+    os.mkdir(dep_model_dir)
+    os.mkdir(pos_model_dir)
+
+    Config.write(dep_model_dir, 'config', features=feat_set, seed=seed,
+                 labels=ArcEager.get_labels(gold_tuples))
+
+    nlp = Language(data_dir=model_dir, tagger=False, parser=False, entity=False)
+    nlp.tagger = Tagger.blank(nlp.vocab, Tagger.default_templates())
+    nlp.parser = Parser.from_dir(dep_model_dir, nlp.vocab.strings, ArcEager)
+ 
+    print("Itn.\tP.Loss\tUAS\tNER F.\tTag %\tToken %")
+    for itn in range(n_iter):
+        scorer = Scorer()
+        loss = 0
+        for _, sents in gold_tuples:
+            for annot_tuples, _ in sents:
+                if len(annot_tuples[1]) == 1:
+                    continue
+
+                score_model(scorer, nlp, None, annot_tuples, verbose=False)
+
+                tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])
+                nlp.tagger(tokens)
+                gold = GoldParse(tokens, annot_tuples, make_projective=True)
+                if not gold.is_projective:
+                    raise Exception(
+                        "Non-projective sentence in training, after we should "
+                        "have enforced projectivity: %s" % annot_tuples
+                    )
+ 
+                loss += nlp.parser.train(tokens, gold)
+                nlp.tagger.train(tokens, gold.tags)
+        random.shuffle(gold_tuples)
+        print('%d:\t%d\t%.3f\t%.3f\t%.3f' % (itn, loss, scorer.uas,
+                                             scorer.tags_acc, scorer.token_acc))
+    print('end training')
+    nlp.end_training(model_dir)
+    print('done')
+
+
+@plac.annotations(
+    train_loc=("Location of CoNLL 09 formatted training file"),
+    dev_loc=("Location of CoNLL 09 formatted development file"),
+    model_dir=("Location of output model directory"),
+    eval_only=("Skip training, and only evaluate", "flag", "e", bool),
+    n_iter=("Number of training iterations", "option", "i", int),
+)
+def main(train_loc, dev_loc, model_dir, n_iter=15):
+    with io.open(train_loc, 'r', encoding='utf8') as file_:
+        train_sents = read_conll(file_)
+    if not eval_only:
+        train(English, train_sents, model_dir, n_iter=n_iter)
+    nlp = English(data_dir=model_dir)
+    dev_sents = read_conll(io.open(dev_loc, 'r', encoding='utf8'))
+    scorer = Scorer()
+    for _, sents in dev_sents:
+        for annot_tuples, _ in sents:
+            score_model(scorer, nlp, None, annot_tuples)
+    print('TOK', 100-scorer.token_acc)
+    print('POS', scorer.tags_acc)
+    print('UAS', scorer.uas)
+    print('LAS', scorer.las)
+
+
+if __name__ == '__main__':
+    plac.call(main)

bin/parser/nn_train.py

@@ -0,0 +1,261 @@
+#!/usr/bin/env python
+from __future__ import division
+from __future__ import unicode_literals
+
+import os
+from os import path
+import shutil
+import codecs
+import random
+
+import plac
+import cProfile
+import pstats
+import re
+
+import spacy.util
+from spacy.en import English
+from spacy.en.pos import POS_TEMPLATES, POS_TAGS, setup_model_dir
+
+from spacy.syntax.util import Config
+from spacy.gold import read_json_file
+from spacy.gold import GoldParse
+
+from spacy.scorer import Scorer
+
+from spacy.syntax.parser import Parser, get_templates
+from spacy._theano import TheanoModel
+
+import theano
+import theano.tensor as T
+
+from theano.printing import Print
+
+import numpy
+from collections import OrderedDict, defaultdict
+
+
+theano.config.profile = False
+theano.config.floatX = 'float32'
+floatX = theano.config.floatX
+
+
+def L1(L1_reg, *weights):
+    return L1_reg * sum(abs(w).sum() for w in weights)
+
+
+def L2(L2_reg, *weights):
+    return L2_reg * sum((w ** 2).sum() for w in weights)
+
+
+def rms_prop(loss, params, eta=1.0, rho=0.9, eps=1e-6):
+    updates = OrderedDict()
+    for param in params:
+        value = param.get_value(borrow=True)
+        accu = theano.shared(np.zeros(value.shape, dtype=value.dtype),
+                             broadcastable=param.broadcastable)
+
+        grad = T.grad(loss, param)
+        accu_new = rho * accu + (1 - rho) * grad ** 2
+        updates[accu] = accu_new
+        updates[param] = param - (eta * grad / T.sqrt(accu_new + eps))
+    return updates
+
+
+def relu(x):
+    return x * (x > 0)
+
+
+def feed_layer(activation, weights, bias, input_):
+    return activation(T.dot(input_, weights) + bias)
+
+
+def init_weights(n_in, n_out):
+    rng = numpy.random.RandomState(1235)
+    
+    weights = numpy.asarray(
+        rng.standard_normal(size=(n_in, n_out)) * numpy.sqrt(2.0 / n_in),
+        dtype=theano.config.floatX
+    )
+    bias = numpy.zeros((n_out,), dtype=theano.config.floatX)
+    return [wrapper(weights, name='W'), wrapper(bias, name='b')]
+
+
+def compile_model(n_classes, n_hidden, n_in, optimizer):
+    x = T.vector('x') 
+    costs = T.ivector('costs')
+    loss = T.scalar('loss')
+
+    maxent_W, maxent_b = init_weights(n_hidden, n_classes)
+    hidden_W, hidden_b = init_weights(n_in, n_hidden)
+
+    # Feed the inputs forward through the network
+    p_y_given_x = feed_layer(
+                    T.nnet.softmax,
+                    maxent_W,
+                    maxent_b,
+                      feed_layer(
+                        relu,
+                        hidden_W,
+                        hidden_b,
+                        x))
+
+    loss = -T.log(T.sum(p_y_given_x[0] * T.eq(costs, 0)) + 1e-8)
+
+    train_model = theano.function(
+        name='train_model',
+        inputs=[x, costs],
+        outputs=[p_y_given_x[0], T.grad(loss, x), loss],
+        updates=optimizer(loss, [maxent_W, maxent_b, hidden_W, hidden_b]),
+        on_unused_input='warn'
+    )
+
+    evaluate_model = theano.function(
+        name='evaluate_model',
+        inputs=[x],
+        outputs=[
+            feed_layer(
+              T.nnet.softmax,
+              maxent_W,
+              maxent_b,
+              feed_layer(
+                relu,
+                hidden_W,
+                hidden_b,
+                x
+              )
+            )[0]
+        ]
+    )
+    return train_model, evaluate_model
+
+
+def score_model(scorer, nlp, annot_tuples, verbose=False):
+    tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])
+    nlp.tagger(tokens)
+    nlp.parser(tokens)
+    gold = GoldParse(tokens, annot_tuples)
+    scorer.score(tokens, gold, verbose=verbose)
+
+
+def train(Language, gold_tuples, model_dir, n_iter=15, feat_set=u'basic',
+          eta=0.01, mu=0.9, nv_hidden=100, nv_word=10, nv_tag=10, nv_label=10,
+          seed=0, n_sents=0,  verbose=False):
+
+    dep_model_dir = path.join(model_dir, 'deps')
+    pos_model_dir = path.join(model_dir, 'pos')
+    if path.exists(dep_model_dir):
+        shutil.rmtree(dep_model_dir)
+    if path.exists(pos_model_dir):
+        shutil.rmtree(pos_model_dir)
+    os.mkdir(dep_model_dir)
+    os.mkdir(pos_model_dir)
+    setup_model_dir(sorted(POS_TAGS.keys()), POS_TAGS, POS_TEMPLATES, pos_model_dir)
+
+    Config.write(dep_model_dir, 'config',
+        seed=seed,
+        templates=tuple(),
+        labels=Language.ParserTransitionSystem.get_labels(gold_tuples),
+        vector_lengths=(nv_word, nv_tag, nv_label),
+        hidden_nodes=nv_hidden,
+        eta=eta,
+        mu=mu
+    )
+  
+    # Bake-in hyper-parameters
+    optimizer = lambda loss, params: rms_prop(loss, params, eta=eta, rho=rho, eps=eps)
+    nlp = Language(data_dir=model_dir)
+    n_classes = nlp.parser.model.n_classes
+    train, predict = compile_model(n_classes, nv_hidden, n_in, optimizer)
+    nlp.parser.model = TheanoModel(n_classes, input_spec, train,
+                                   predict, model_loc)
+ 
+    if n_sents > 0:
+        gold_tuples = gold_tuples[:n_sents]
+    print "Itn.\tP.Loss\tUAS\tTag %\tToken %"
+    log_loc = path.join(model_dir, 'job.log')
+    for itn in range(n_iter):
+        scorer = Scorer()
+        loss = 0
+        for _, sents in gold_tuples:
+            for annot_tuples, ctnt in sents:
+                if len(annot_tuples[1]) == 1:
+                    continue
+                score_model(scorer, nlp, annot_tuples)
+                tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])
+                nlp.tagger(tokens)
+                gold = GoldParse(tokens, annot_tuples, make_projective=True)
+                assert gold.is_projective
+                loss += nlp.parser.train(tokens, gold)
+                nlp.tagger.train(tokens, gold.tags)
+        random.shuffle(gold_tuples)
+        logline = '%d:\t%d\t%.3f\t%.3f\t%.3f' % (itn, loss, scorer.uas,
+                                                 scorer.tags_acc,
+                                                 scorer.token_acc)
+        print logline
+        with open(log_loc, 'aw') as file_:
+            file_.write(logline + '\n')
+    nlp.parser.model.end_training()
+    nlp.tagger.model.end_training()
+    nlp.vocab.strings.dump(path.join(model_dir, 'vocab', 'strings.txt'))
+    return nlp
+
+
+def evaluate(nlp, gold_tuples, gold_preproc=True):
+    scorer = Scorer()
+    for raw_text, sents in gold_tuples:
+        for annot_tuples, brackets in sents:
+            tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])
+            nlp.tagger(tokens)
+            nlp.parser(tokens)
+            gold = GoldParse(tokens, annot_tuples)
+            scorer.score(tokens, gold)
+    return scorer
+
+
+@plac.annotations(
+    train_loc=("Location of training file or directory"),
+    dev_loc=("Location of development file or directory"),
+    model_dir=("Location of output model directory",),
+    eval_only=("Skip training, and only evaluate", "flag", "e", bool),
+    n_sents=("Number of training sentences", "option", "n", int),
+    n_iter=("Number of training iterations", "option", "i", int),
+    verbose=("Verbose error reporting", "flag", "v", bool),
+
+    nv_word=("Word vector length", "option", "W", int),
+    nv_tag=("Tag vector length", "option", "T", int),
+    nv_label=("Label vector length", "option", "L", int),
+    nv_hidden=("Hidden nodes length", "option", "H", int),
+    eta=("Learning rate", "option", "E", float),
+    mu=("Momentum", "option", "M", float),
+)
+def main(train_loc, dev_loc, model_dir, n_sents=0, n_iter=15, verbose=False,
+         nv_word=10, nv_tag=10, nv_label=10, nv_hidden=10,
+         eta=0.1, mu=0.9, eval_only=False):
+
+
+
+
+    gold_train = list(read_json_file(train_loc, lambda doc: 'wsj' in doc['id']))
+
+    nlp = train(English, gold_train, model_dir,
+               feat_set='embed',
+               eta=eta, mu=mu,
+               nv_word=nv_word, nv_tag=nv_tag, nv_label=nv_label, nv_hidden=nv_hidden,
+               n_sents=n_sents, n_iter=n_iter,
+               verbose=verbose)
+
+    scorer = evaluate(nlp, list(read_json_file(dev_loc)))
+    
+    print 'TOK', 100-scorer.token_acc
+    print 'POS', scorer.tags_acc
+    print 'UAS', scorer.uas
+    print 'LAS', scorer.las
+
+    print 'NER P', scorer.ents_p
+    print 'NER R', scorer.ents_r
+    print 'NER F', scorer.ents_f
+
+
+if __name__ == '__main__':
+    plac.call(main)

bin/parser/train.py

@@ -0,0 +1,246 @@
+#!/usr/bin/env python
+from __future__ import division
+from __future__ import unicode_literals
+from __future__ import print_function
+
+import os
+from os import path
+import shutil
+import io
+import random
+
+import plac
+import re
+
+import spacy.util
+
+from spacy.syntax.util import Config
+from spacy.gold import read_json_file
+from spacy.gold import GoldParse
+
+from spacy.scorer import Scorer
+
+from spacy.syntax.arc_eager import ArcEager
+from spacy.syntax.ner import BiluoPushDown
+from spacy.tagger import Tagger
+from spacy.syntax.parser import Parser
+from spacy.syntax.nonproj import PseudoProjectivity
+
+
+def _corrupt(c, noise_level):
+    if random.random() >= noise_level:
+        return c
+    elif c == ' ':
+        return '\n'
+    elif c == '\n':
+        return ' '
+    elif c in ['.', "'", "!", "?"]:
+        return ''
+    else:
+        return c.lower()
+
+
+def add_noise(orig, noise_level):
+    if random.random() >= noise_level:
+        return orig
+    elif type(orig) == list:
+        corrupted = [_corrupt(word, noise_level) for word in orig]
+        corrupted = [w for w in corrupted if w]
+        return corrupted
+    else:
+        return ''.join(_corrupt(c, noise_level) for c in orig)
+
+
+def score_model(scorer, nlp, raw_text, annot_tuples, verbose=False):
+    if raw_text is None:
+        tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])
+    else:
+        tokens = nlp.tokenizer(raw_text)
+    nlp.tagger(tokens)
+    nlp.entity(tokens)
+    nlp.parser(tokens)
+    gold = GoldParse(tokens, annot_tuples)
+    scorer.score(tokens, gold, verbose=verbose)
+
+
+def _merge_sents(sents):
+    m_deps = [[], [], [], [], [], []]
+    m_brackets = []
+    i = 0
+    for (ids, words, tags, heads, labels, ner), brackets in sents:
+        m_deps[0].extend(id_ + i for id_ in ids)
+        m_deps[1].extend(words)
+        m_deps[2].extend(tags)
+        m_deps[3].extend(head + i for head in heads)
+        m_deps[4].extend(labels)
+        m_deps[5].extend(ner)
+        m_brackets.extend((b['first'] + i, b['last'] + i, b['label']) for b in brackets)
+        i += len(ids)
+    return [(m_deps, m_brackets)]
+
+
+def train(Language, gold_tuples, model_dir, n_iter=15, feat_set=u'basic',
+          seed=0, gold_preproc=False, n_sents=0, corruption_level=0,
+          beam_width=1, verbose=False,
+          use_orig_arc_eager=False, pseudoprojective=False):
+    dep_model_dir = path.join(model_dir, 'deps')
+    ner_model_dir = path.join(model_dir, 'ner')
+    pos_model_dir = path.join(model_dir, 'pos')
+    if path.exists(dep_model_dir):
+        shutil.rmtree(dep_model_dir)
+    if path.exists(ner_model_dir):
+        shutil.rmtree(ner_model_dir)
+    if path.exists(pos_model_dir):
+        shutil.rmtree(pos_model_dir)
+    os.mkdir(dep_model_dir)
+    os.mkdir(ner_model_dir)
+    os.mkdir(pos_model_dir)
+
+    if pseudoprojective:
+        # preprocess training data here before ArcEager.get_labels() is called
+        gold_tuples = PseudoProjectivity.preprocess_training_data(gold_tuples)
+
+    Config.write(dep_model_dir, 'config', features=feat_set, seed=seed,
+                 labels=ArcEager.get_labels(gold_tuples),
+                 beam_width=beam_width,projectivize=pseudoprojective)
+    Config.write(ner_model_dir, 'config', features='ner', seed=seed,
+                 labels=BiluoPushDown.get_labels(gold_tuples),
+                 beam_width=0)
+
+    if n_sents > 0:
+        gold_tuples = gold_tuples[:n_sents]
+
+    nlp = Language(data_dir=model_dir, tagger=False, parser=False, entity=False)
+    nlp.tagger = Tagger.blank(nlp.vocab, Tagger.default_templates())
+    nlp.parser = Parser.from_dir(dep_model_dir, nlp.vocab.strings, ArcEager)
+    nlp.entity = Parser.from_dir(ner_model_dir, nlp.vocab.strings, BiluoPushDown)
+    print("Itn.\tP.Loss\tUAS\tNER F.\tTag %\tToken %")
+    for itn in range(n_iter):
+        scorer = Scorer()
+        loss = 0
+        for raw_text, sents in gold_tuples:
+            if gold_preproc:
+                raw_text = None
+            else:
+                sents = _merge_sents(sents)
+            for annot_tuples, ctnt in sents:
+                if len(annot_tuples[1]) == 1:
+                    continue
+                score_model(scorer, nlp, raw_text, annot_tuples,
+                            verbose=verbose if itn >= 2 else False)
+                if raw_text is None:
+                    words = add_noise(annot_tuples[1], corruption_level)
+                    tokens = nlp.tokenizer.tokens_from_list(words)
+                else:
+                    raw_text = add_noise(raw_text, corruption_level)
+                    tokens = nlp.tokenizer(raw_text)
+                nlp.tagger(tokens)
+                gold = GoldParse(tokens, annot_tuples)
+                if not gold.is_projective:
+                    raise Exception("Non-projective sentence in training: %s" % annot_tuples[1])
+                loss += nlp.parser.train(tokens, gold)
+                nlp.entity.train(tokens, gold)
+                nlp.tagger.train(tokens, gold.tags)
+        random.shuffle(gold_tuples)
+        print('%d:\t%d\t%.3f\t%.3f\t%.3f\t%.3f' % (itn, loss, scorer.uas, scorer.ents_f,
+                                                   scorer.tags_acc,
+                                                   scorer.token_acc))
+    print('end training')
+    nlp.end_training(model_dir)
+    print('done')
+
+
+def evaluate(Language, gold_tuples, model_dir, gold_preproc=False, verbose=False,
+             beam_width=None, cand_preproc=None):
+    nlp = Language(data_dir=model_dir)
+    if nlp.lang == 'de':
+        nlp.vocab.morphology.lemmatizer = lambda string,pos: set([string])
+    if beam_width is not None:
+        nlp.parser.cfg.beam_width = beam_width
+    scorer = Scorer()
+    for raw_text, sents in gold_tuples:
+        if gold_preproc:
+            raw_text = None
+        else:
+            sents = _merge_sents(sents)
+        for annot_tuples, brackets in sents:
+            if raw_text is None:
+                tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])
+                nlp.tagger(tokens)
+                nlp.parser(tokens)
+                nlp.entity(tokens)
+            else:
+                tokens = nlp(raw_text)
+            gold = GoldParse(tokens, annot_tuples)
+            scorer.score(tokens, gold, verbose=verbose)
+    return scorer
+
+
+def write_parses(Language, dev_loc, model_dir, out_loc):
+    nlp = Language(data_dir=model_dir)
+    gold_tuples = read_json_file(dev_loc)
+    scorer = Scorer()
+    out_file = io.open(out_loc, 'w', 'utf8')
+    for raw_text, sents in gold_tuples:
+        sents = _merge_sents(sents)
+        for annot_tuples, brackets in sents:
+            if raw_text is None:
+                tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])
+                nlp.tagger(tokens)
+                nlp.entity(tokens)
+                nlp.parser(tokens)
+            else:
+                tokens = nlp(raw_text)
+            #gold = GoldParse(tokens, annot_tuples)
+            #scorer.score(tokens, gold, verbose=False)
+            for sent in tokens.sents:
+                for t in sent:
+                    if not t.is_space:
+                        out_file.write(
+                            '%d\t%s\t%s\t%s\t%s\n' % (t.i, t.orth_, t.tag_, t.head.orth_, t.dep_)
+                        )
+                out_file.write('\n')
+
+
+@plac.annotations(
+    language=("The language to train", "positional", None, str, ['en','de', 'zh']),
+    train_loc=("Location of training file or directory"),
+    dev_loc=("Location of development file or directory"),
+    model_dir=("Location of output model directory",),
+    eval_only=("Skip training, and only evaluate", "flag", "e", bool),
+    corruption_level=("Amount of noise to add to training data", "option", "c", float),
+    gold_preproc=("Use gold-standard sentence boundaries in training?", "flag", "g", bool),
+    out_loc=("Out location", "option", "o", str),
+    n_sents=("Number of training sentences", "option", "n", int),
+    n_iter=("Number of training iterations", "option", "i", int),
+    verbose=("Verbose error reporting", "flag", "v", bool),
+    debug=("Debug mode", "flag", "d", bool),
+    pseudoprojective=("Use pseudo-projective parsing", "flag", "p", bool),
+)
+def main(language, train_loc, dev_loc, model_dir, n_sents=0, n_iter=15, out_loc="", verbose=False,
+         debug=False, corruption_level=0.0, gold_preproc=False, eval_only=False, pseudoprojective=False):
+    lang = spacy.util.get_lang_class(language)
+
+    if not eval_only:
+        gold_train = list(read_json_file(train_loc))
+        train(lang, gold_train, model_dir,
+              feat_set='basic' if not debug else 'debug',
+              gold_preproc=gold_preproc, n_sents=n_sents,
+              corruption_level=corruption_level, n_iter=n_iter,
+              verbose=verbose,pseudoprojective=pseudoprojective)
+    if out_loc:
+        write_parses(lang, dev_loc, model_dir, out_loc)
+    scorer = evaluate(lang, list(read_json_file(dev_loc)),
+                      model_dir, gold_preproc=gold_preproc, verbose=verbose)
+    print('TOK', scorer.token_acc)
+    print('POS', scorer.tags_acc)
+    print('UAS', scorer.uas)
+    print('LAS', scorer.las)
+
+    print('NER P', scorer.ents_p)
+    print('NER R', scorer.ents_r)
+    print('NER F', scorer.ents_f)
+
+
+if __name__ == '__main__':
+    plac.call(main)

bin/parser/train_ud.py

@@ -0,0 +1,161 @@
+import plac
+import json
+from os import path
+import shutil
+import os
+import random
+import io
+
+from spacy.syntax.util import Config
+from spacy.gold import GoldParse
+from spacy.tokenizer import Tokenizer
+from spacy.vocab import Vocab
+from spacy.tagger import Tagger
+from spacy.syntax.parser import Parser
+from spacy.syntax.arc_eager import ArcEager
+from spacy.syntax.parser import get_templates
+from spacy.scorer import Scorer
+import spacy.attrs
+
+from spacy.language import Language
+
+from spacy.tagger import W_orth
+
+TAGGER_TEMPLATES = (
+    (W_orth,),
+)
+
+try:
+    from codecs import open
+except ImportError:
+    pass
+
+
+class TreebankParser(object):
+    @staticmethod
+    def setup_model_dir(model_dir, labels, templates, feat_set='basic', seed=0):
+        dep_model_dir = path.join(model_dir, 'deps')
+        pos_model_dir = path.join(model_dir, 'pos')
+        if path.exists(dep_model_dir):
+            shutil.rmtree(dep_model_dir)
+        if path.exists(pos_model_dir):
+            shutil.rmtree(pos_model_dir)
+        os.mkdir(dep_model_dir)
+        os.mkdir(pos_model_dir)
+
+        Config.write(dep_model_dir, 'config', features=feat_set, seed=seed,
+                     labels=labels)
+
+    @classmethod
+    def from_dir(cls, tag_map, model_dir):
+        vocab = Vocab(tag_map=tag_map, get_lex_attr=Language.default_lex_attrs())
+        vocab.get_lex_attr[spacy.attrs.LANG] = lambda _: 0
+        tokenizer = Tokenizer(vocab, {}, None, None, None)
+        tagger = Tagger.blank(vocab, TAGGER_TEMPLATES)
+
+        cfg = Config.read(path.join(model_dir, 'deps'), 'config')
+        parser = Parser.from_dir(path.join(model_dir, 'deps'), vocab.strings, ArcEager)
+        return cls(vocab, tokenizer, tagger, parser)
+
+    def __init__(self, vocab, tokenizer, tagger, parser):
+        self.vocab = vocab
+        self.tokenizer = tokenizer
+        self.tagger = tagger
+        self.parser = parser
+
+    def train(self, words, tags, heads, deps):
+        tokens = self.tokenizer.tokens_from_list(list(words))
+        self.tagger.train(tokens, tags)
+        
+        tokens = self.tokenizer.tokens_from_list(list(words))
+        ids = range(len(words))
+        ner = ['O'] * len(words)
+        gold = GoldParse(tokens, ((ids, words, tags, heads, deps, ner)),
+                         make_projective=False)
+        self.tagger(tokens)
+        if gold.is_projective:
+            try:
+                self.parser.train(tokens, gold)
+            except:
+                for id_, word, head, dep in zip(ids, words, heads, deps):
+                    print(id_, word, head, dep)
+                raise
+
+    def __call__(self, words, tags=None):
+        tokens = self.tokenizer.tokens_from_list(list(words))
+        if tags is None:
+            self.tagger(tokens)
+        else:
+            self.tagger.tag_from_strings(tokens, tags)
+        self.parser(tokens)
+        return tokens
+
+    def end_training(self, data_dir):
+        self.parser.model.end_training()
+        self.parser.model.dump(path.join(data_dir, 'deps', 'model'))
+        self.tagger.model.end_training()
+        self.tagger.model.dump(path.join(data_dir, 'pos', 'model'))
+        strings_loc = path.join(data_dir, 'vocab', 'strings.json')
+        with io.open(strings_loc, 'w', encoding='utf8') as file_:
+            self.vocab.strings.dump(file_)
+        self.vocab.dump(path.join(data_dir, 'vocab', 'lexemes.bin'))
+
+
+ 
+
+def read_conllx(loc):
+    with open(loc, 'r', 'utf8') as file_:
+        text = file_.read()
+    for sent in text.strip().split('\n\n'):
+        lines = sent.strip().split('\n')
+        if lines:
+            while lines[0].startswith('#'):
+                lines.pop(0)
+            tokens = []
+            for line in lines:
+                id_, word, lemma, pos, tag, morph, head, dep, _1, _2 = line.split()
+                if '-' in id_:
+                    continue
+                id_ = int(id_) - 1
+                head = (int(head) - 1) if head != '0' else id_
+                dep = 'ROOT' if dep == 'root' else dep
+                tokens.append((id_, word, tag, head, dep, 'O'))
+            tuples = zip(*tokens)
+            yield (None, [(tuples, [])])
+
+
+def score_model(nlp, gold_docs, verbose=False):
+    scorer = Scorer()
+    for _, gold_doc in gold_docs:
+        for annot_tuples, _ in gold_doc:
+            tokens = nlp(list(annot_tuples[1]), tags=list(annot_tuples[2]))
+            gold = GoldParse(tokens, annot_tuples)
+            scorer.score(tokens, gold, verbose=verbose)
+    return scorer
+
+
+def main(train_loc, dev_loc, model_dir, tag_map_loc):
+    with open(tag_map_loc) as file_:
+        tag_map = json.loads(file_.read())
+    train_sents = list(read_conllx(train_loc))
+    labels = ArcEager.get_labels(train_sents)
+    templates = get_templates('basic')
+
+    TreebankParser.setup_model_dir(model_dir, labels, templates)
+    
+    nlp = TreebankParser.from_dir(tag_map, model_dir)
+
+    for itn in range(15):
+        for _, doc_sents in train_sents:
+            for (ids, words, tags, heads, deps, ner), _ in doc_sents:
+                nlp.train(words, tags, heads, deps)
+        random.shuffle(train_sents)
+        scorer = score_model(nlp, read_conllx(dev_loc))
+        print('%d:\t%.3f\t%.3f' % (itn, scorer.uas, scorer.tags_acc))
+    nlp.end_training(model_dir)
+    scorer = score_model(nlp, read_conllx(dev_loc))
+    print('%d:\t%.3f\t%.3f\t%.3f' % (itn, scorer.uas, scorer.las, scorer.tags_acc))
+ 
+
+if __name__ == '__main__':
+    plac.call(main)

bin/prepare_treebank.py

@@ -0,0 +1,194 @@
+"""Convert OntoNotes into a json format.
+
+doc: {
+    id: string,
+    paragraphs: [{
+        raw: string,
+        sents: [int],
+        tokens: [{
+            start: int,
+            tag: string,
+            head: int,
+            dep: string}],
+        ner: [{
+            start: int,
+            end: int,
+            label: string}],
+        brackets: [{
+            start: int,
+            end: int,
+            label: string}]}]}
+
+Consumes output of spacy/munge/align_raw.py
+"""
+from __future__ import unicode_literals
+import plac
+import json
+from os import path
+import os
+import re
+import io
+from collections import defaultdict
+
+from spacy.munge import read_ptb
+from spacy.munge import read_conll
+from spacy.munge import read_ner
+
+
+def _iter_raw_files(raw_loc):
+    files = json.load(open(raw_loc))
+    for f in files:
+        yield f
+
+
+def format_doc(file_id, raw_paras, ptb_text, dep_text, ner_text):
+    ptb_sents = read_ptb.split(ptb_text)
+    dep_sents = read_conll.split(dep_text)
+    if len(ptb_sents) != len(dep_sents):
+        return None
+    if ner_text is not None:
+        ner_sents = read_ner.split(ner_text)
+    else:
+        ner_sents = [None] * len(ptb_sents)
+
+    i = 0
+    doc = {'id': file_id}
+    if raw_paras is None:
+        doc['paragraphs'] = [format_para(None, ptb_sents, dep_sents, ner_sents)]
+        #for ptb_sent, dep_sent, ner_sent in zip(ptb_sents, dep_sents, ner_sents):
+        #    doc['paragraphs'].append(format_para(None, [ptb_sent], [dep_sent], [ner_sent]))
+    else:
+        doc['paragraphs'] = []
+        for raw_sents in raw_paras:
+            para = format_para(
+                        ' '.join(raw_sents).replace('<SEP>', ''),
+                        ptb_sents[i:i+len(raw_sents)],
+                        dep_sents[i:i+len(raw_sents)],
+                        ner_sents[i:i+len(raw_sents)])
+            if para['sentences']:
+                doc['paragraphs'].append(para)
+            i += len(raw_sents)
+    return doc
+
+
+def format_para(raw_text, ptb_sents, dep_sents, ner_sents):
+    para = {'raw': raw_text, 'sentences': []}
+    offset = 0
+    assert len(ptb_sents) == len(dep_sents) == len(ner_sents)
+    for ptb_text, dep_text, ner_text in zip(ptb_sents, dep_sents, ner_sents):
+        _, deps = read_conll.parse(dep_text, strip_bad_periods=True)
+        if deps and 'VERB' in [t['tag'] for t in deps]:
+            continue
+        if ner_text is not None:
+            _, ner = read_ner.parse(ner_text, strip_bad_periods=True)
+        else:
+            ner = ['-' for _ in deps]
+        _, brackets = read_ptb.parse(ptb_text, strip_bad_periods=True)
+        # Necessary because the ClearNLP converter deletes EDITED words.
+        if len(ner) != len(deps):
+            ner = ['-' for _ in deps]
+        para['sentences'].append(format_sentence(deps, ner, brackets))
+    return para
+
+
+def format_sentence(deps, ner, brackets):
+    sent = {'tokens': [], 'brackets': []}
+    for token_id, (token, token_ent) in enumerate(zip(deps, ner)):
+        sent['tokens'].append(format_token(token_id, token, token_ent))
+
+    for label, start, end in brackets:
+        if start != end:
+            sent['brackets'].append({
+                'label': label,
+                'first': start,
+                'last': (end-1)})
+    return sent
+
+
+def format_token(token_id, token, ner):
+    assert token_id == token['id']
+    head = (token['head'] - token_id) if token['head'] != -1 else 0
+    return {
+        'id': token_id,
+        'orth': token['word'],
+        'tag': token['tag'],
+        'head': head,
+        'dep': token['dep'],
+        'ner': ner}
+
+
+def read_file(*pieces):
+    loc = path.join(*pieces)
+    if not path.exists(loc):
+        return None
+    else:
+        return io.open(loc, 'r', encoding='utf8').read().strip()
+
+
+def get_file_names(section_dir, subsection):
+    filenames = []
+    for fn in os.listdir(path.join(section_dir, subsection)):
+        filenames.append(fn.rsplit('.', 1)[0])
+    return list(sorted(set(filenames)))
+
+
+def read_wsj_with_source(onto_dir, raw_dir):
+    # Now do WSJ, with source alignment
+    onto_dir = path.join(onto_dir, 'data', 'english', 'annotations', 'nw', 'wsj')
+    docs = {}
+    for i in range(25):
+        section = str(i) if i >= 10 else ('0' + str(i))
+        raw_loc = path.join(raw_dir, 'wsj%s.json' % section)
+        for j, (filename, raw_paras) in enumerate(_iter_raw_files(raw_loc)):
+            if section == '00':
+                j += 1
+            if section == '04' and filename == '55':
+                continue
+            ptb = read_file(onto_dir, section, '%s.parse' % filename)
+            dep = read_file(onto_dir, section, '%s.parse.dep' % filename)
+            ner = read_file(onto_dir, section, '%s.name' % filename)
+            if ptb is not None and dep is not None:
+                docs[filename] = format_doc(filename, raw_paras, ptb, dep, ner)
+    return docs
+
+
+def get_doc(onto_dir, file_path, wsj_docs):
+    filename = file_path.rsplit('/', 1)[1]
+    if filename in wsj_docs:
+        return wsj_docs[filename]
+    else:
+        ptb = read_file(onto_dir, file_path + '.parse')
+        dep = read_file(onto_dir, file_path + '.parse.dep')
+        ner = read_file(onto_dir, file_path + '.name')
+        if ptb is not None and dep is not None:
+            return format_doc(filename, None, ptb, dep, ner)
+        else:
+            return None
+
+
+def read_ids(loc):
+    return open(loc).read().strip().split('\n')
+
+
+def main(onto_dir, raw_dir, out_dir):
+    wsj_docs = read_wsj_with_source(onto_dir, raw_dir)
+
+    for partition in ('train', 'test', 'development'):
+        ids = read_ids(path.join(onto_dir, '%s.id' % partition))
+        docs_by_genre = defaultdict(list)
+        for file_path in ids:
+            doc = get_doc(onto_dir, file_path, wsj_docs)
+            if doc is not None:
+                genre = file_path.split('/')[3]
+                docs_by_genre[genre].append(doc)
+        part_dir = path.join(out_dir, partition)
+        if not path.exists(part_dir):
+            os.mkdir(part_dir)
+        for genre, docs in sorted(docs_by_genre.items()):
+            out_loc = path.join(part_dir, genre + '.json')
+            with open(out_loc, 'w') as file_:
+                json.dump(docs, file_, indent=4)
+
+
+if __name__ == '__main__':
+    plac.call(main)

bin/prepare_vecs.py

@@ -0,0 +1,13 @@
+"""Read a vector file, and prepare it as binary data, for easy consumption"""
+
+import plac
+
+from spacy.vocab import write_binary_vectors
+
+
+def main(in_loc, out_loc):
+    write_binary_vectors(in_loc, out_loc)
+
+
+if __name__ == '__main__':
+    plac.call(main)

bin/tagger/train.py

@@ -0,0 +1,175 @@
+#!/usr/bin/env python
+from __future__ import division
+from __future__ import unicode_literals
+from __future__ import print_function
+
+import os
+from os import path
+import shutil
+import codecs
+import random
+
+import plac
+import re
+
+import spacy.util
+from spacy.en import English
+
+from spacy.tagger import Tagger
+
+from spacy.syntax.util import Config
+from spacy.gold import read_json_file
+from spacy.gold import GoldParse
+
+from spacy.scorer import Scorer
+
+
+def score_model(scorer, nlp, raw_text, annot_tuples):
+    if raw_text is None:
+        tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])
+    else:
+        tokens = nlp.tokenizer(raw_text)
+    nlp.tagger(tokens)
+    gold = GoldParse(tokens, annot_tuples)
+    scorer.score(tokens, gold)
+
+
+def _merge_sents(sents):
+    m_deps = [[], [], [], [], [], []]
+    m_brackets = []
+    i = 0
+    for (ids, words, tags, heads, labels, ner), brackets in sents:
+        m_deps[0].extend(id_ + i for id_ in ids)
+        m_deps[1].extend(words)
+        m_deps[2].extend(tags)
+        m_deps[3].extend(head + i for head in heads)
+        m_deps[4].extend(labels)
+        m_deps[5].extend(ner)
+        m_brackets.extend((b['first'] + i, b['last'] + i, b['label']) for b in brackets)
+        i += len(ids)
+    return [(m_deps, m_brackets)]
+
+
+def train(Language, gold_tuples, model_dir, n_iter=15, feat_set=u'basic',
+          seed=0, gold_preproc=False, n_sents=0, corruption_level=0,
+          beam_width=1, verbose=False,
+          use_orig_arc_eager=False):
+    if n_sents > 0:
+        gold_tuples = gold_tuples[:n_sents]
+   
+    templates = Tagger.default_templates()
+    nlp = Language(data_dir=model_dir, tagger=False)
+    nlp.tagger = Tagger.blank(nlp.vocab, templates)
+
+    print("Itn.\tP.Loss\tUAS\tNER F.\tTag %\tToken %")
+    for itn in range(n_iter):
+        scorer = Scorer()
+        loss = 0
+        for raw_text, sents in gold_tuples:
+            if gold_preproc:
+                raw_text = None
+            else:
+                sents = _merge_sents(sents)
+            for annot_tuples, ctnt in sents:
+                words = annot_tuples[1]
+                gold_tags = annot_tuples[2]
+                score_model(scorer, nlp, raw_text, annot_tuples)
+                if raw_text is None:
+                    tokens = nlp.tokenizer.tokens_from_list(words)
+                else:
+                    tokens = nlp.tokenizer(raw_text)
+                loss += nlp.tagger.train(tokens, gold_tags)
+        random.shuffle(gold_tuples)
+        print('%d:\t%d\t%.3f\t%.3f\t%.3f\t%.3f' % (itn, loss, scorer.uas, scorer.ents_f,
+                                                   scorer.tags_acc,
+                                                   scorer.token_acc))
+    nlp.end_training(model_dir)
+
+def evaluate(Language, gold_tuples, model_dir, gold_preproc=False, verbose=False,
+             beam_width=None):
+    nlp = Language(data_dir=model_dir)
+    if beam_width is not None:
+        nlp.parser.cfg.beam_width = beam_width
+    scorer = Scorer()
+    for raw_text, sents in gold_tuples:
+        if gold_preproc:
+            raw_text = None
+        else:
+            sents = _merge_sents(sents)
+        for annot_tuples, brackets in sents:
+            if raw_text is None:
+                tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])
+                nlp.tagger(tokens)
+                nlp.entity(tokens)
+                nlp.parser(tokens)
+            else:
+                tokens = nlp(raw_text, merge_mwes=False)
+            gold = GoldParse(tokens, annot_tuples)
+            scorer.score(tokens, gold, verbose=verbose)
+    return scorer
+
+
+def write_parses(Language, dev_loc, model_dir, out_loc, beam_width=None):
+    nlp = Language(data_dir=model_dir)
+    if beam_width is not None:
+        nlp.parser.cfg.beam_width = beam_width
+    gold_tuples = read_json_file(dev_loc)
+    scorer = Scorer()
+    out_file = codecs.open(out_loc, 'w', 'utf8')
+    for raw_text, sents in gold_tuples:
+        sents = _merge_sents(sents)
+        for annot_tuples, brackets in sents:
+            if raw_text is None:
+                tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])
+                nlp.tagger(tokens)
+                nlp.entity(tokens)
+                nlp.parser(tokens)
+            else:
+                tokens = nlp(raw_text, merge_mwes=False)
+            gold = GoldParse(tokens, annot_tuples)
+            scorer.score(tokens, gold, verbose=False)
+            for t in tokens:
+                out_file.write(
+                    '%s\t%s\t%s\t%s\n' % (t.orth_, t.tag_, t.head.orth_, t.dep_)
+                )
+    return scorer
+
+
+@plac.annotations(
+    train_loc=("Location of training file or directory"),
+    dev_loc=("Location of development file or directory"),
+    model_dir=("Location of output model directory",),
+    eval_only=("Skip training, and only evaluate", "flag", "e", bool),
+    corruption_level=("Amount of noise to add to training data", "option", "c", float),
+    gold_preproc=("Use gold-standard sentence boundaries in training?", "flag", "g", bool),
+    out_loc=("Out location", "option", "o", str),
+    n_sents=("Number of training sentences", "option", "n", int),
+    n_iter=("Number of training iterations", "option", "i", int),
+    verbose=("Verbose error reporting", "flag", "v", bool),
+    debug=("Debug mode", "flag", "d", bool),
+)
+def main(train_loc, dev_loc, model_dir, n_sents=0, n_iter=15, out_loc="", verbose=False,
+         debug=False, corruption_level=0.0, gold_preproc=False, eval_only=False):
+    if not eval_only:
+        gold_train = list(read_json_file(train_loc))
+        train(English, gold_train, model_dir,
+              feat_set='basic' if not debug else 'debug',
+              gold_preproc=gold_preproc, n_sents=n_sents,
+              corruption_level=corruption_level, n_iter=n_iter,
+              verbose=verbose)
+    #if out_loc:
+    #    write_parses(English, dev_loc, model_dir, out_loc, beam_width=beam_width)
+    scorer = evaluate(English, list(read_json_file(dev_loc)),
+                      model_dir, gold_preproc=gold_preproc, verbose=verbose)
+    print('TOK', scorer.token_acc)
+    print('POS', scorer.tags_acc)
+    print('UAS', scorer.uas)
+    print('LAS', scorer.las)
+
+    print('NER P', scorer.ents_p)
+    print('NER R', scorer.ents_r)
+    print('NER F', scorer.ents_f)
+
+
+if __name__ == '__main__':
+    plac.call(main)

bin/tagger/train_german_tagger.py

@@ -0,0 +1,160 @@
+#!/usr/bin/env python
+from __future__ import division
+from __future__ import unicode_literals
+
+import os
+from os import path
+import shutil
+import io
+import random
+import time
+import gzip
+import ujson
+
+import plac
+import cProfile
+import pstats
+
+import spacy.util
+from spacy.de import German
+from spacy.gold import GoldParse
+from spacy.tagger import Tagger
+from spacy.scorer import PRFScore
+
+from spacy.tagger import P2_orth, P2_cluster, P2_shape, P2_prefix, P2_suffix, P2_pos, P2_lemma, P2_flags 
+from spacy.tagger import P1_orth, P1_cluster, P1_shape, P1_prefix, P1_suffix, P1_pos, P1_lemma, P1_flags 
+from spacy.tagger import W_orth, W_cluster, W_shape, W_prefix, W_suffix, W_pos, W_lemma, W_flags
+from spacy.tagger import N1_orth, N1_cluster, N1_shape, N1_prefix, N1_suffix, N1_pos, N1_lemma, N1_flags
+from spacy.tagger import N2_orth, N2_cluster, N2_shape, N2_prefix, N2_suffix, N2_pos, N2_lemma, N2_flags, N_CONTEXT_FIELDS
+
+
+def default_templates():
+    return spacy.tagger.Tagger.default_templates()
+
+def default_templates_without_clusters():
+    return (
+        (W_orth,),
+        (P1_lemma, P1_pos),
+        (P2_lemma, P2_pos),
+        (N1_orth,),
+        (N2_orth,),
+
+        (W_suffix,),
+        (W_prefix,),
+
+        (P1_pos,),
+        (P2_pos,),
+        (P1_pos, P2_pos),
+        (P1_pos, W_orth),
+        (P1_suffix,),
+        (N1_suffix,),
+
+        (W_shape,),
+
+        (W_flags,),
+        (N1_flags,),
+        (N2_flags,),
+        (P1_flags,),
+        (P2_flags,),
+    )
+
+
+def make_tagger(vocab, templates):
+    model = spacy.tagger.TaggerModel(templates)
+    return spacy.tagger.Tagger(vocab,model)
+
+
+def read_conll(file_):
+    def sentences():
+        words, tags = [], []
+        for line in file_:
+            line = line.strip()
+            if line:
+                word, tag = line.split('\t')[1::3][:2] # get column 1 and 4 (CoNLL09)
+                words.append(word)
+                tags.append(tag)
+            elif words:
+                yield words, tags
+                words, tags = [], []
+        if words:
+            yield words, tags
+    return [ s for s in sentences() ]
+
+        
+def score_model(score, nlp, words, gold_tags):
+    tokens = nlp.tokenizer.tokens_from_list(words)
+    assert(len(tokens) == len(gold_tags))
+    nlp.tagger(tokens)
+
+    for token, gold_tag in zip(tokens,gold_tags):
+        score.score_set(set([token.tag_]),set([gold_tag]))
+
+
+def train(Language, train_sents, dev_sents, model_dir, n_iter=15, seed=21):
+    # make shuffling deterministic
+    random.seed(seed)
+
+    # set up directory for model
+    pos_model_dir = path.join(model_dir, 'pos')
+    if path.exists(pos_model_dir):
+        shutil.rmtree(pos_model_dir)
+    os.mkdir(pos_model_dir)
+
+    nlp = Language(data_dir=model_dir, tagger=False, parser=False, entity=False)
+    nlp.tagger = make_tagger(nlp.vocab,default_templates())
+     
+    print("Itn.\ttrain acc %\tdev acc %")
+    for itn in range(n_iter):
+        # train on train set
+        #train_acc = PRFScore()
+        correct, total = 0., 0.
+        for words, gold_tags in train_sents:
+            tokens = nlp.tokenizer.tokens_from_list(words)
+            correct += nlp.tagger.train(tokens, gold_tags)
+            total += len(words)
+        train_acc = correct/total
+
+        # test on dev set
+        dev_acc = PRFScore()
+        for words, gold_tags in dev_sents:
+            score_model(dev_acc, nlp, words, gold_tags)
+
+        random.shuffle(train_sents)
+        print('%d:\t%6.2f\t%6.2f' % (itn, 100*train_acc, 100*dev_acc.precision))
+
+
+    print('end training')
+    nlp.end_training(model_dir)
+    print('done')
+
+
+@plac.annotations(
+    train_loc=("Location of CoNLL 09 formatted training file"),
+    dev_loc=("Location of CoNLL 09 formatted development file"),
+    model_dir=("Location of output model directory"),
+    eval_only=("Skip training, and only evaluate", "flag", "e", bool),
+    n_iter=("Number of training iterations", "option", "i", int),
+)
+def main(train_loc, dev_loc, model_dir, eval_only=False, n_iter=15):
+    # training
+    if not eval_only:
+        with io.open(train_loc, 'r', encoding='utf8') as trainfile_, \
+             io.open(dev_loc, 'r', encoding='utf8') as devfile_:
+            train_sents = read_conll(trainfile_)
+            dev_sents = read_conll(devfile_)
+        train(German, train_sents, dev_sents, model_dir, n_iter=n_iter)
+
+    # testing
+    with io.open(dev_loc, 'r', encoding='utf8') as file_:
+        dev_sents = read_conll(file_)
+        nlp = German(data_dir=model_dir)
+
+        dev_acc = PRFScore()
+        for words, gold_tags in dev_sents:
+            score_model(dev_acc, nlp, words, gold_tags)                
+        
+        print('POS: %6.2f %%' % (100*dev_acc.precision))
+
+
+if __name__ == '__main__':
+    plac.call(main)

buildbot.json

@@ -0,0 +1,25 @@
+{
+    "build": {
+        "sdist": [
+            "pip install -r requirements.txt",
+            "pip install \"numpy<1.8\"",
+            "python setup.py sdist"
+        ],
+        "install": [
+            "pip install -v source.tar.gz"
+        ],
+        "wheel": [
+            "python untar.py source.tar.gz .",
+            "python setup.py bdist_wheel",
+            "python cpdist.py dist"
+        ]
+    },
+    "test": {
+        "after": ["install", "wheel"],
+        "run": [
+            "python -m spacy.en.download --force"
+        ],
+        "package": "spacy",
+        "args": "--tb=native -x --models --vectors --slow"
+    }
+}

contributors/NSchrading.md

@@ -0,0 +1,95 @@
+Syllogism Contributor Agreement
+===============================
+
+This Syllogism Contributor Agreement (“SCA”) is based on the Oracle Contributor
+Agreement. The SCA applies to any contribution that you make to any product or
+project managed by us (the “project”), and sets out the intellectual property
+rights you grant to us in the contributed materials. The term “us” shall mean
+Syllogism Co. The term "you" shall mean the person or entity identified below.
+If you agree to be bound by these terms, fill in the information requested below
+and include the filled-in version with your first pull-request, under the file
+contrbutors/. The name of the file should be your GitHub username, with the
+extension .md. For example, the user example_user would create the file
+spaCy/contributors/example_user.md .
+
+Read this agreement carefully before signing. These terms and conditions
+constitute a binding legal agreement.
+
+1. The term 'contribution' or ‘contributed materials’ means any source code,
+object code, patch, tool, sample, graphic, specification, manual, documentation,
+or any other material posted or submitted by you to the project.
+
+2. With respect to any worldwide copyrights, or copyright applications and registrations,
+in your contribution:
+  * you hereby assign to us joint ownership, and to the extent that such assignment
+  is or becomes invalid, ineffective or unenforceable, you hereby grant to us a perpetual,
+  irrevocable, non-exclusive, worldwide, no-charge, royalty-free, unrestricted license
+  to exercise all rights under those copyrights. This includes, at our option, the
+  right to sublicense these same rights to third parties through multiple levels of
+  sublicensees or other licensing arrangements;
+
+  * you agree that each of us can do all things in relation to your contribution
+  as if each of us were the sole owners, and if one of us makes a derivative work
+  of your contribution, the one who makes the derivative work (or has it made) will
+  be the sole owner of that derivative work;
+
+  * you agree that you will not assert any moral rights in your contribution against
+  us, our licensees or transferees;
+  
+  * you agree that we may register a copyright in your contribution and exercise
+  all ownership rights associated with it; and
+
+  * you agree that neither of us has any duty to consult with, obtain the consent
+  of, pay or render an accounting to the other for any use or distribution of your
+  contribution.
+
+3. With respect to any patents you own, or that you can license without payment
+to any third party, you hereby grant to us a perpetual, irrevocable, non-exclusive,
+worldwide, no-charge, royalty-free license to:
+
+  * make, have made, use, sell, offer to sell, import, and otherwise transfer your
+  contribution in whole or in part, alone or in combination with
+  or included in any product, work or materials arising out of the project to
+  which your contribution was submitted, and
+
+  * at our option, to sublicense these same rights to third parties through multiple
+  levels of sublicensees or other licensing arrangements.
+
+4. Except as set out above, you keep all right, title, and interest in your
+contribution. The rights that you grant to us under these terms are effective on
+the date you first submitted a contribution to us, even if your submission took
+place before the date you sign these terms.
+
+5. You covenant, represent, warrant and agree that:
+
+  * Each contribution that you submit is and shall be an original work of authorship
+  and you can legally grant the rights set out in this SCA;
+  
+  * to the best of your knowledge, each contribution will not violate any third
+  party's copyrights, trademarks, patents, or other intellectual property rights; and
+
+  * each contribution shall be in compliance with U.S. export control laws and other
+  applicable export and import laws. You agree to notify us if you become aware of
+  any circumstance which would make any of the foregoing representations inaccurate
+  in any respect. Syllogism Co. may publicly disclose your participation in the project,
+  including the fact that you have signed the SCA.
+
+6. This SCA is governed by the laws of the State of California and applicable U.S.
+  Federal law. Any choice of law rules will not apply.
+
+7. Please place an “x” on one of the applicable statement below. Please do NOT
+mark both statements:
+
+_x__ I am signing on behalf of myself as an individual and no other person or entity, including my employer, has or will have rights with respect my contributions.
+
+____ I am signing on behalf of my employer or a legal entity and I have the actual authority to contractually bind that entity.
+
+| Field                          | Entry                |
+|------------------------------- | -------------------- |
+| Name                           | J Nicolas Schrading  |
+| Company's name (if applicable) |                      |
+| Title or Role (if applicable)  |                      |
+| Date                           | 2015-08-24           |
+| GitHub username                | NSchrading           |
+| Website (optional)             | nicschrading.com     |
+

contributors/chrisdubois.md

@@ -0,0 +1,95 @@
+Syllogism Contributor Agreement
+===============================
+
+This Syllogism Contributor Agreement (“SCA”) is based on the Oracle Contributor
+Agreement. The SCA applies to any contribution that you make to any product or
+project managed by us (the “project”), and sets out the intellectual property
+rights you grant to us in the contributed materials. The term “us” shall mean
+Syllogism Co. The term "you" shall mean the person or entity identified below.
+If you agree to be bound by these terms, fill in the information requested below
+and include the filled-in version with your first pull-request, under the file
+contrbutors/. The name of the file should be your GitHub username, with the
+extension .md. For example, the user example_user would create the file
+spaCy/contributors/example_user.md .
+
+Read this agreement carefully before signing. These terms and conditions
+constitute a binding legal agreement.
+
+1. The term 'contribution' or ‘contributed materials’ means any source code,
+object code, patch, tool, sample, graphic, specification, manual, documentation,
+or any other material posted or submitted by you to the project.
+
+2. With respect to any worldwide copyrights, or copyright applications and registrations,
+in your contribution:
+  * you hereby assign to us joint ownership, and to the extent that such assignment
+  is or becomes invalid, ineffective or unenforceable, you hereby grant to us a perpetual,
+  irrevocable, non-exclusive, worldwide, no-charge, royalty-free, unrestricted license
+  to exercise all rights under those copyrights. This includes, at our option, the
+  right to sublicense these same rights to third parties through multiple levels of
+  sublicensees or other licensing arrangements;
+
+  * you agree that each of us can do all things in relation to your contribution
+  as if each of us were the sole owners, and if one of us makes a derivative work
+  of your contribution, the one who makes the derivative work (or has it made) will
+  be the sole owner of that derivative work;
+
+  * you agree that you will not assert any moral rights in your contribution against
+  us, our licensees or transferees;
+  
+  * you agree that we may register a copyright in your contribution and exercise
+  all ownership rights associated with it; and
+
+  * you agree that neither of us has any duty to consult with, obtain the consent
+  of, pay or render an accounting to the other for any use or distribution of your
+  contribution.
+
+3. With respect to any patents you own, or that you can license without payment
+to any third party, you hereby grant to us a perpetual, irrevocable, non-exclusive,
+worldwide, no-charge, royalty-free license to:
+
+  * make, have made, use, sell, offer to sell, import, and otherwise transfer your
+  contribution in whole or in part, alone or in combination with
+  or included in any product, work or materials arising out of the project to
+  which your contribution was submitted, and
+
+  * at our option, to sublicense these same rights to third parties through multiple
+  levels of sublicensees or other licensing arrangements.
+
+4. Except as set out above, you keep all right, title, and interest in your
+contribution. The rights that you grant to us under these terms are effective on
+the date you first submitted a contribution to us, even if your submission took
+place before the date you sign these terms.
+
+5. You covenant, represent, warrant and agree that:
+
+  * Each contribution that you submit is and shall be an original work of authorship
+  and you can legally grant the rights set out in this SCA;
+  
+  * to the best of your knowledge, each contribution will not violate any third
+  party's copyrights, trademarks, patents, or other intellectual property rights; and
+
+  * each contribution shall be in compliance with U.S. export control laws and other
+  applicable export and import laws. You agree to notify us if you become aware of
+  any circumstance which would make any of the foregoing representations inaccurate
+  in any respect. Syllogism Co. may publicly disclose your participation in the project,
+  including the fact that you have signed the SCA.
+
+6. This SCA is governed by the laws of the State of California and applicable U.S.
+  Federal law. Any choice of law rules will not apply.
+
+7. Please place an “x” on one of the applicable statement below. Please do NOT
+mark both statements:
+
+x I am signing on behalf of myself as an individual and no other person or entity, including my employer, has or will have rights with respect my contributions.
+
+____ I am signing on behalf of my employer or a legal entity and I have the actual authority to contractually bind that entity.
+
+| Field                          | Entry                |
+|------------------------------- | -------------------- |
+| Name                           | Chris DuBois         |
+| Company's name (if applicable) |                      |
+| Title or Role (if applicable)  |                      |
+| Date                           | 2015.10.07           |
+| GitHub username                | chrisdubois          |
+| Website (optional)             |                      |
+

contributors/cla.md

@@ -0,0 +1,13 @@
+Signing the Contributors License Agreement
+==========================================
+
+SpaCy is a commercial open-source project, owned by Syllogism Co. We require that contributors to SpaCy sign our Contributors License Agreement, which is based on the Oracle Contributor Agreement.
+
+The CLA must be signed on your first pull request. To do this, simply fill in the file cla_template.md, and include the filed in form in your first pull request.
+
+    $ git clone https://github.com/honnibal/spaCy
+    $ cp spaCy/contributors/cla_template.md spaCy/contributors/<your GitHub username>.md
+    <Now fill in the file spaCy/contributors/<your GitHub username>.md>
+    $ git add -A spaCy/contributors/<your GitHub username>.md
+    
+Now finish your pull request, and you're done.

contributors/cla_template.md

@@ -0,0 +1,95 @@
+Syllogism Contributor Agreement
+===============================
+
+This Syllogism Contributor Agreement (“SCA”) is based on the Oracle Contributor
+Agreement. The SCA applies to any contribution that you make to any product or
+project managed by us (the “project”), and sets out the intellectual property
+rights you grant to us in the contributed materials. The term “us” shall mean
+Syllogism Co. The term "you" shall mean the person or entity identified below.
+If you agree to be bound by these terms, fill in the information requested below
+and include the filled-in version with your first pull-request, under the file
+contrbutors/. The name of the file should be your GitHub username, with the
+extension .md. For example, the user example_user would create the file
+spaCy/contributors/example_user.md .
+
+Read this agreement carefully before signing. These terms and conditions
+constitute a binding legal agreement.
+
+1. The term 'contribution' or ‘contributed materials’ means any source code,
+object code, patch, tool, sample, graphic, specification, manual, documentation,
+or any other material posted or submitted by you to the project.
+
+2. With respect to any worldwide copyrights, or copyright applications and registrations,
+in your contribution:
+  * you hereby assign to us joint ownership, and to the extent that such assignment
+  is or becomes invalid, ineffective or unenforceable, you hereby grant to us a perpetual,
+  irrevocable, non-exclusive, worldwide, no-charge, royalty-free, unrestricted license
+  to exercise all rights under those copyrights. This includes, at our option, the
+  right to sublicense these same rights to third parties through multiple levels of
+  sublicensees or other licensing arrangements;
+
+  * you agree that each of us can do all things in relation to your contribution
+  as if each of us were the sole owners, and if one of us makes a derivative work
+  of your contribution, the one who makes the derivative work (or has it made) will
+  be the sole owner of that derivative work;
+
+  * you agree that you will not assert any moral rights in your contribution against
+  us, our licensees or transferees;
+  
+  * you agree that we may register a copyright in your contribution and exercise
+  all ownership rights associated with it; and
+
+  * you agree that neither of us has any duty to consult with, obtain the consent
+  of, pay or render an accounting to the other for any use or distribution of your
+  contribution.
+
+3. With respect to any patents you own, or that you can license without payment
+to any third party, you hereby grant to us a perpetual, irrevocable, non-exclusive,
+worldwide, no-charge, royalty-free license to:
+
+  * make, have made, use, sell, offer to sell, import, and otherwise transfer your
+  contribution in whole or in part, alone or in combination with
+  or included in any product, work or materials arising out of the project to
+  which your contribution was submitted, and
+
+  * at our option, to sublicense these same rights to third parties through multiple
+  levels of sublicensees or other licensing arrangements.
+
+4. Except as set out above, you keep all right, title, and interest in your
+contribution. The rights that you grant to us under these terms are effective on
+the date you first submitted a contribution to us, even if your submission took
+place before the date you sign these terms.
+
+5. You covenant, represent, warrant and agree that:
+
+  * Each contribution that you submit is and shall be an original work of authorship
+  and you can legally grant the rights set out in this SCA;
+  
+  * to the best of your knowledge, each contribution will not violate any third
+  party's copyrights, trademarks, patents, or other intellectual property rights; and
+
+  * each contribution shall be in compliance with U.S. export control laws and other
+  applicable export and import laws. You agree to notify us if you become aware of
+  any circumstance which would make any of the foregoing representations inaccurate
+  in any respect. Syllogism Co. may publicly disclose your participation in the project,
+  including the fact that you have signed the SCA.
+
+6. This SCA is governed by the laws of the State of California and applicable U.S.
+  Federal law. Any choice of law rules will not apply.
+
+7. Please place an “x” on one of the applicable statement below. Please do NOT
+mark both statements:
+
+____ I am signing on behalf of myself as an individual and no other person or entity, including my employer, has or will have rights with respect my contributions.
+
+____ I am signing on behalf of my employer or a legal entity and I have the actual authority to contractually bind that entity.
+
+| Field                          | Entry                |
+|------------------------------- | -------------------- |
+| Name                           |                      |
+| Company's name (if applicable) |                      |
+| Title or Role (if applicable)  |                      |
+| Date                           |                      |
+| GitHub username                |                      |
+| Website (optional)             |                      |
+

contributors/suchow.md

@@ -0,0 +1,95 @@
+Syllogism Contributor Agreement
+===============================
+
+This Syllogism Contributor Agreement (“SCA”) is based on the Oracle Contributor
+Agreement. The SCA applies to any contribution that you make to any product or
+project managed by us (the “project”), and sets out the intellectual property
+rights you grant to us in the contributed materials. The term “us” shall mean
+Syllogism Co. The term "you" shall mean the person or entity identified below.
+If you agree to be bound by these terms, fill in the information requested below
+and include the filled-in version with your first pull-request, under the file
+contrbutors/. The name of the file should be your GitHub username, with the
+extension .md. For example, the user example_user would create the file
+spaCy/contributors/example_user.md .
+
+Read this agreement carefully before signing. These terms and conditions
+constitute a binding legal agreement.
+
+1. The term 'contribution' or ‘contributed materials’ means any source code,
+object code, patch, tool, sample, graphic, specification, manual, documentation,
+or any other material posted or submitted by you to the project.
+
+2. With respect to any worldwide copyrights, or copyright applications and registrations,
+in your contribution:
+  * you hereby assign to us joint ownership, and to the extent that such assignment
+  is or becomes invalid, ineffective or unenforceable, you hereby grant to us a perpetual,
+  irrevocable, non-exclusive, worldwide, no-charge, royalty-free, unrestricted license
+  to exercise all rights under those copyrights. This includes, at our option, the
+  right to sublicense these same rights to third parties through multiple levels of
+  sublicensees or other licensing arrangements;
+
+  * you agree that each of us can do all things in relation to your contribution
+  as if each of us were the sole owners, and if one of us makes a derivative work
+  of your contribution, the one who makes the derivative work (or has it made) will
+  be the sole owner of that derivative work;
+
+  * you agree that you will not assert any moral rights in your contribution against
+  us, our licensees or transferees;
+  
+  * you agree that we may register a copyright in your contribution and exercise
+  all ownership rights associated with it; and
+
+  * you agree that neither of us has any duty to consult with, obtain the consent
+  of, pay or render an accounting to the other for any use or distribution of your
+  contribution.
+
+3. With respect to any patents you own, or that you can license without payment
+to any third party, you hereby grant to us a perpetual, irrevocable, non-exclusive,
+worldwide, no-charge, royalty-free license to:
+
+  * make, have made, use, sell, offer to sell, import, and otherwise transfer your
+  contribution in whole or in part, alone or in combination with
+  or included in any product, work or materials arising out of the project to
+  which your contribution was submitted, and
+
+  * at our option, to sublicense these same rights to third parties through multiple
+  levels of sublicensees or other licensing arrangements.
+
+4. Except as set out above, you keep all right, title, and interest in your
+contribution. The rights that you grant to us under these terms are effective on
+the date you first submitted a contribution to us, even if your submission took
+place before the date you sign these terms.
+
+5. You covenant, represent, warrant and agree that:
+
+  * Each contribution that you submit is and shall be an original work of authorship
+  and you can legally grant the rights set out in this SCA;
+  
+  * to the best of your knowledge, each contribution will not violate any third
+  party's copyrights, trademarks, patents, or other intellectual property rights; and
+
+  * each contribution shall be in compliance with U.S. export control laws and other
+  applicable export and import laws. You agree to notify us if you become aware of
+  any circumstance which would make any of the foregoing representations inaccurate
+  in any respect. Syllogism Co. may publicly disclose your participation in the project,
+  including the fact that you have signed the SCA.
+
+6. This SCA is governed by the laws of the State of California and applicable U.S.
+  Federal law. Any choice of law rules will not apply.
+
+7. Please place an “x” on one of the applicable statement below. Please do NOT
+mark both statements:
+
+x___ I am signing on behalf of myself as an individual and no other person or entity, including my employer, has or will have rights with respect my contributions.
+
+____ I am signing on behalf of my employer or a legal entity and I have the actual authority to contractually bind that entity.
+
+| Field                          | Entry                |
+|------------------------------- | -------------------- |
+| Name                           | Jordan Suchow        |
+| Company's name (if applicable) |                      |
+| Title or Role (if applicable)  |                      |
+| Date                           | 2015-04-19           |
+| GitHub username                | suchow               |
+| Website (optional)             | http://suchow.io     |
+

contributors/vsolovyov.md

@@ -0,0 +1,95 @@
+Syllogism Contributor Agreement
+===============================
+
+This Syllogism Contributor Agreement (“SCA”) is based on the Oracle Contributor
+Agreement. The SCA applies to any contribution that you make to any product or
+project managed by us (the “project”), and sets out the intellectual property
+rights you grant to us in the contributed materials. The term “us” shall mean
+Syllogism Co. The term "you" shall mean the person or entity identified below.
+If you agree to be bound by these terms, fill in the information requested below
+and include the filled-in version with your first pull-request, under the file
+contrbutors/. The name of the file should be your GitHub username, with the
+extension .md. For example, the user example_user would create the file
+spaCy/contributors/example_user.md .
+
+Read this agreement carefully before signing. These terms and conditions
+constitute a binding legal agreement.
+
+1. The term 'contribution' or ‘contributed materials’ means any source code,
+object code, patch, tool, sample, graphic, specification, manual, documentation,
+or any other material posted or submitted by you to the project.
+
+2. With respect to any worldwide copyrights, or copyright applications and registrations,
+in your contribution:
+  * you hereby assign to us joint ownership, and to the extent that such assignment
+  is or becomes invalid, ineffective or unenforceable, you hereby grant to us a perpetual,
+  irrevocable, non-exclusive, worldwide, no-charge, royalty-free, unrestricted license
+  to exercise all rights under those copyrights. This includes, at our option, the
+  right to sublicense these same rights to third parties through multiple levels of
+  sublicensees or other licensing arrangements;
+
+  * you agree that each of us can do all things in relation to your contribution
+  as if each of us were the sole owners, and if one of us makes a derivative work
+  of your contribution, the one who makes the derivative work (or has it made) will
+  be the sole owner of that derivative work;
+
+  * you agree that you will not assert any moral rights in your contribution against
+  us, our licensees or transferees;
+  
+  * you agree that we may register a copyright in your contribution and exercise
+  all ownership rights associated with it; and
+
+  * you agree that neither of us has any duty to consult with, obtain the consent
+  of, pay or render an accounting to the other for any use or distribution of your
+  contribution.
+
+3. With respect to any patents you own, or that you can license without payment
+to any third party, you hereby grant to us a perpetual, irrevocable, non-exclusive,
+worldwide, no-charge, royalty-free license to:
+
+  * make, have made, use, sell, offer to sell, import, and otherwise transfer your
+  contribution in whole or in part, alone or in combination with
+  or included in any product, work or materials arising out of the project to
+  which your contribution was submitted, and
+
+  * at our option, to sublicense these same rights to third parties through multiple
+  levels of sublicensees or other licensing arrangements.
+
+4. Except as set out above, you keep all right, title, and interest in your
+contribution. The rights that you grant to us under these terms are effective on
+the date you first submitted a contribution to us, even if your submission took
+place before the date you sign these terms.
+
+5. You covenant, represent, warrant and agree that:
+
+  * Each contribution that you submit is and shall be an original work of authorship
+  and you can legally grant the rights set out in this SCA;
+  
+  * to the best of your knowledge, each contribution will not violate any third
+  party's copyrights, trademarks, patents, or other intellectual property rights; and
+
+  * each contribution shall be in compliance with U.S. export control laws and other
+  applicable export and import laws. You agree to notify us if you become aware of
+  any circumstance which would make any of the foregoing representations inaccurate
+  in any respect. Syllogism Co. may publicly disclose your participation in the project,
+  including the fact that you have signed the SCA.
+
+6. This SCA is governed by the laws of the State of California and applicable U.S.
+  Federal law. Any choice of law rules will not apply.
+
+7. Please place an “x” on one of the applicable statement below. Please do NOT
+mark both statements:
+
+_x__ I am signing on behalf of myself as an individual and no other person or entity, including my employer, has or will have rights with respect my contributions.
+
+____ I am signing on behalf of my employer or a legal entity and I have the actual authority to contractually bind that entity.
+
+| Field                          | Entry                |
+|------------------------------- | -------------------- |
+| Name                           | Vsevolod Solovyov    |
+| Company's name (if applicable) |                      |
+| Title or Role (if applicable)  |                      |
+| Date                           | 2015-08-24           |
+| GitHub username                | vsolovyov            |
+| Website (optional)             |                      |
+

corpora/en/wordnet/AUTHORS

@@ -0,0 +1,6 @@
+Cognitive Science Laboratory
+Princeton University
+
+http://wordnet.princeton.edu
+wordnet@princeton.edu
+

corpora/en/wordnet/COPYING

@@ -0,0 +1,31 @@
+WordNet Release 3.0
+
+This software and database is being provided to you, the LICENSEE, by  
+Princeton University under the following license.  By obtaining, using  
+and/or copying this software and database, you agree that you have  
+read, understood, and will comply with these terms and conditions.:  
+  
+Permission to use, copy, modify and distribute this software and  
+database and its documentation for any purpose and without fee or  
+royalty is hereby granted, provided that you agree to comply with  
+the following copyright notice and statements, including the disclaimer,  
+and that the same appear on ALL copies of the software, database and  
+documentation, including modifications that you make for internal  
+use or for distribution.  
+  
+WordNet 3.0 Copyright 2006 by Princeton University.  All rights reserved.  
+  
+THIS SOFTWARE AND DATABASE IS PROVIDED "AS IS" AND PRINCETON  
+UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR  
+IMPLIED.  BY WAY OF EXAMPLE, BUT NOT LIMITATION, PRINCETON  
+UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES OF MERCHANT-  
+ABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OR THAT THE USE  
+OF THE LICENSED SOFTWARE, DATABASE OR DOCUMENTATION WILL NOT  
+INFRINGE ANY THIRD PARTY PATENTS, COPYRIGHTS, TRADEMARKS OR  
+OTHER RIGHTS.  
+  
+The name of Princeton University or Princeton may not be used in  
+advertising or publicity pertaining to distribution of the software  
+and/or database.  Title to copyright in this software, database and  
+any associated documentation shall at all times remain with  
+Princeton University and LICENSEE agrees to preserve same.  

corpora/en/wordnet/ChangeLog

@@ -0,0 +1,9 @@
+Changes between WordNet 2.1 and 3.0
+
+Some changes were made to the graphical interface and WordNet library
+with regard to adjective and adverb searches.  The adjective search
+"Synonyms/Related Nouns" was relabeled "Synonyms", and, similarly, the
+adverb search "Synonyms/Stem Adjectives" was relabled "Synonyms".  A
+separate "Related Noun" search was inserted for adjectives, and a
+separate "Base Adjective" search was added for adverbs.
+

corpora/en/wordnet/INSTALL

@@ -0,0 +1,312 @@
+
+		WordNet 3.0 Installation Instructions
+
+Beginning with Version 2.1, we have changed the Unix package to a GNU
+Autotools package.  With Autotools, a system independent installation
+process builds and installs WordNet on your specific platform.  Read
+both the `Basic Installation' and `WordNet Installation' sections
+below before attempting to build and install WordNet.
+
+See the `Running WordNet' section for important information concerning
+environment variables and the commands to run WordNet.
+
+The WordNet browser makes use of the open source Tcl and Tk
+packages. Many systems come with either or both pre-installed.  If
+your system doesn't (some systems have Tcl installed, but not Tk)
+Tcl/Tk can be downloaded from:
+
+Linux - http://www.tcl.tk/ 
+
+OS X - http://tcltkaqua.sourceforge.net/ (note that 10.4 comes with
+Tcl/Tk preinstalled, but earlier versions may not)
+
+Some Linux systems come with the Tcl/Tk libraries installed, but not
+all the header files. If your build fails due to missing Tk headers, a
+subset that may be sufficient on your system can be found in the
+"include/tk" directory. Copy the header files to the "include" directory
+and try the make again.  If it fails, you should download and install
+a full copy of Tcl and/or Tk from the site above.
+
+Tcl and Tk must be installed BEFORE you build and install WordNet. You
+must also have a C compiler before installing Tcl/Tk or WordNet.
+WordNet has been built and tested with the GNU gcc compiler.  This is
+pre-installed on most Unix systems, and can be downloaded from:
+
+http://gcc.gnu.org/
+
+Basic Installation
+==================
+
+********************************************************************
+   These are generic installation instructions. Details specific to
+   WordNet follow in the `WordNet Installation' section below.
+********************************************************************
+
+   The `configure' shell script attempts to guess correct values for
+various system-dependent variables used during compilation.  It uses
+those values to create a `Makefile' in each directory of the package.
+It may also create one or more `.h' files containing system-dependent
+definitions.  Finally, it creates a shell script `config.status' that
+you can run in the future to recreate the current configuration, and a
+file `config.log' containing compiler output (useful mainly for
+debugging `configure').
+
+   It can also use an optional file (typically called `config.cache'
+and enabled with `--cache-file=config.cache' or simply `-C') that saves
+the results of its tests to speed up reconfiguring.  (Caching is
+disabled by default to prevent problems with accidental use of stale
+cache files.)
+
+The simplest way to compile this package is:
+
+  1. `cd' to the directory containing the package's source code and type
+     `./configure' to configure the package for your system.  If you're
+     using `csh' on an old version of System V, you might need to type
+     `sh ./configure' instead to prevent `csh' from trying to execute
+     `configure' itself.
+
+     Running `configure' takes awhile.  While running, it prints some
+     messages telling which features it is checking for.
+
+  2. Type `make' to compile the package.
+
+  3. Type `make install' to install the programs and any data files and
+     documentation.
+
+  4. You can remove the program binaries and object files from the
+     source code directory by typing `make clean'.  To also remove the
+     files that `configure' created (so you can compile the package for
+     a different kind of computer), type `make distclean'.  There is
+     also a `make maintainer-clean' target, but that is intended mainly
+     for the package's developers.  If you use it, you may have to get
+     all sorts of other programs in order to regenerate files that came
+     with the distribution.
+
+Compilers and Options
+=====================
+
+   Some systems require unusual options for compilation or linking that
+the `configure' script does not know about.  Run `./configure --help'
+for details on some of the pertinent environment variables.
+
+   You can give `configure' initial values for configuration parameters
+by setting variables in the command line or in the environment.  Here
+is an example:
+
+     ./configure CC=c89 CFLAGS=-O2 LIBS=-lposix
+
+   *Note Defining Variables::, for more details.
+
+Compiling For Multiple Architectures
+====================================
+
+   You can compile the package for more than one kind of computer at the
+same time, by placing the object files for each architecture in their
+own directory.  To do this, you must use a version of `make' that
+supports the `VPATH' variable, such as GNU `make'.  `cd' to the
+directory where you want the object files and executables to go and run
+the `configure' script.  `configure' automatically checks for the
+source code in the directory that `configure' is in and in `..'.
+
+   If you have to use a `make' that does not support the `VPATH'
+variable, you have to compile the package for one architecture at a
+time in the source code directory.  After you have installed the
+package for one architecture, use `make distclean' before reconfiguring
+for another architecture.
+
+Installation Names
+==================
+
+   By default, `make install' will install the package's files in
+`/usr/local/bin', `/usr/local/man', etc.  You can specify an
+installation prefix other than `/usr/local' by giving `configure' the
+option `--prefix=PATH'.
+
+   You can specify separate installation prefixes for
+architecture-specific files and architecture-independent files.  If you
+give `configure' the option `--exec-prefix=PATH', the package will use
+PATH as the prefix for installing programs and libraries.
+Documentation and other data files will still use the regular prefix.
+
+   In addition, if you use an unusual directory layout you can give
+options like `--bindir=PATH' to specify different values for particular
+kinds of files.  Run `configure --help' for a list of the directories
+you can set and what kinds of files go in them.
+
+   If the package supports it, you can cause programs to be installed
+with an extra prefix or suffix on their names by giving `configure' the
+option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'.
+
+Optional Features
+=================
+
+   Some packages pay attention to `--enable-FEATURE' options to
+`configure', where FEATURE indicates an optional part of the package.
+They may also pay attention to `--with-PACKAGE' options, where PACKAGE
+is something like `gnu-as' or `x' (for the X Window System).  The
+`README' should mention any `--enable-' and `--with-' options that the
+package recognizes.
+
+   For packages that use the X Window System, `configure' can usually
+find the X include and library files automatically, but if it doesn't,
+you can use the `configure' options `--x-includes=DIR' and
+`--x-libraries=DIR' to specify their locations.
+
+Specifying the System Type
+==========================
+
+   There may be some features `configure' cannot figure out
+automatically, but needs to determine by the type of machine the package
+will run on.  Usually, assuming the package is built to be run on the
+_same_ architectures, `configure' can figure that out, but if it prints
+a message saying it cannot guess the machine type, give it the
+`--build=TYPE' option.  TYPE can either be a short name for the system
+type, such as `sun4', or a canonical name which has the form:
+
+     CPU-COMPANY-SYSTEM
+
+where SYSTEM can have one of these forms:
+
+     OS KERNEL-OS
+
+   See the file `config.sub' for the possible values of each field.  If
+`config.sub' isn't included in this package, then this package doesn't
+need to know the machine type.
+
+   If you are _building_ compiler tools for cross-compiling, you should
+use the `--target=TYPE' option to select the type of system they will
+produce code for.
+
+   If you want to _use_ a cross compiler, that generates code for a
+platform different from the build platform, you should specify the
+"host" platform (i.e., that on which the generated programs will
+eventually be run) with `--host=TYPE'.
+
+Sharing Defaults
+================
+
+   If you want to set default values for `configure' scripts to share,
+you can create a site shell script called `config.site' that gives
+default values for variables like `CC', `cache_file', and `prefix'.
+`configure' looks for `PREFIX/share/config.site' if it exists, then
+`PREFIX/etc/config.site' if it exists.  Or, you can set the
+`CONFIG_SITE' environment variable to the location of the site script.
+A warning: not all `configure' scripts look for a site script.
+
+Defining Variables
+==================
+
+   Variables not defined in a site shell script can be set in the
+environment passed to `configure'.  However, some packages may run
+configure again during the build, and the customized values of these
+variables may be lost.  In order to avoid this problem, you should set
+them in the `configure' command line, using `VAR=value'.  For example:
+
+     ./configure CC=/usr/local2/bin/gcc
+
+will cause the specified gcc to be used as the C compiler (unless it is
+overridden in the site shell script).
+
+`configure' Invocation
+======================
+
+   `configure' recognizes the following options to control how it
+operates.
+
+`--help'
+`-h'
+     Print a summary of the options to `configure', and exit.
+
+`--version'
+`-V'
+     Print the version of Autoconf used to generate the `configure'
+     script, and exit.
+
+`--cache-file=FILE'
+     Enable the cache: use and save the results of the tests in FILE,
+     traditionally `config.cache'.  FILE defaults to `/dev/null' to
+     disable caching.
+
+`--config-cache'
+`-C'
+     Alias for `--cache-file=config.cache'.
+
+`--quiet'
+`--silent'
+`-q'
+     Do not print messages saying which checks are being made.  To
+     suppress all normal output, redirect it to `/dev/null' (any error
+     messages will still be shown).
+
+`--srcdir=DIR'
+     Look for the package's source code in directory DIR.  Usually
+     `configure' can determine that directory automatically.
+
+`configure' also accepts some other, not widely useful, options.  Run
+`configure --help' for more details.
+
+
+WordNet Installation
+====================
+
+By default, WordNet is installed in `/usr/local/WordNet-3.0'.  You
+must usually be the `root' user to install something here.  If you
+choose to install WordNet in a different location, you must use the
+`--prefix=' option to `configure' and specify an installation
+directory.
+
+WordNet relies on the Tcl/Tk package, which you must have installed on
+your system prior to building the WordNet package.  If you have
+installed Tcl/Tk in a non-standard location, you must specify the
+`--with-tcl=' and `--with-tk=' options to `configure' and specify the
+directory that contains the `tclConfig.sh' and `tkConfig.sh'
+configuration scripts, respectively. (Note that these are usually the
+same directories.)
+
+If you're running OS X and installed the Aqua Tcl/Tk package from the
+web site above, use the following settings:
+
+     --with-tcl=/Library/Frameworks/Tcl.framework
+     --with-tk=/Library/Frameworks/Tk.framework
+
+If `configure' can't find either `tclConfig.sh' or `tkConfig.sh', it
+will print an error and stop processing.
+
+After successfully running `configure', you must then build and
+install WordNet using these commands:
+
+make
+make install
+
+Running WordNet
+===============
+
+In order to run WordNet, you must set your PATH variable to include
+the directory that contains the WordNet binraries. By default, WordNet
+is installed in `/usr/local/WordNet-3.0'.  
+
+Several other environment variables may need to be set in order to
+run WordNet on your system:
+
+PATH - should include either `/usr/local/WordNet-3.0/bin' or the path
+you specified with the `--prefix=' option to `configure', unless you
+installed WordNet in a directory that is already in your path.
+
+WNHOME - if you did not install in the default location, you must set
+this environment variable to the value you specified on the `prefix='
+option.  This tells the WordNet browser where to find the database files.
+
+LD_LIBRARY_PATH - may need to be set to the location of the Tcl/Tk
+libraries.
+
+TK_LIBRARY - on OS X, may need to be set to the directory that
+contains the `tk.tcl' file (usually a subidrectory of where the Tk
+library is installed).
+
+The command `wnb' starts the WordNet browser application.  If any
+of the above variables is not set, or not set properly, an error will
+occur when you run `wnb'.
+
+The command line interface is run with the `wn' command.  The `PATH' and
+`WNHOME' environment variables must also be set.
+

corpora/en/wordnet/LICENSE

@@ -0,0 +1,31 @@
+WordNet Release 3.0
+
+This software and database is being provided to you, the LICENSEE, by  
+Princeton University under the following license.  By obtaining, using  
+and/or copying this software and database, you agree that you have  
+read, understood, and will comply with these terms and conditions.:  
+  
+Permission to use, copy, modify and distribute this software and  
+database and its documentation for any purpose and without fee or  
+royalty is hereby granted, provided that you agree to comply with  
+the following copyright notice and statements, including the disclaimer,  
+and that the same appear on ALL copies of the software, database and  
+documentation, including modifications that you make for internal  
+use or for distribution.  
+  
+WordNet 3.0 Copyright 2006 by Princeton University.  All rights reserved.  
+  
+THIS SOFTWARE AND DATABASE IS PROVIDED "AS IS" AND PRINCETON  
+UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR  
+IMPLIED.  BY WAY OF EXAMPLE, BUT NOT LIMITATION, PRINCETON  
+UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES OF MERCHANT-  
+ABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OR THAT THE USE  
+OF THE LICENSED SOFTWARE, DATABASE OR DOCUMENTATION WILL NOT  
+INFRINGE ANY THIRD PARTY PATENTS, COPYRIGHTS, TRADEMARKS OR  
+OTHER RIGHTS.  
+  
+The name of Princeton University or Princeton may not be used in  
+advertising or publicity pertaining to distribution of the software  
+and/or database.  Title to copyright in this software, database and  
+any associated documentation shall at all times remain with  
+Princeton University and LICENSEE agrees to preserve same.  

corpora/en/wordnet/Makefile.am

@@ -0,0 +1,2 @@
+EXTRA_DIST = README ChangeLog COPYING INSTALL AUTHORS LICENSE doc dict include
+SUBDIRS = doc dict include lib src

corpora/en/wordnet/Makefile.in

@@ -0,0 +1,569 @@
+# Makefile.in generated by automake 1.9 from Makefile.am.
+# @configure_input@
+
+# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
+# 2003, 2004  Free Software Foundation, Inc.
+# This Makefile.in is free software; the Free Software Foundation
+# gives unlimited permission to copy and/or distribute it,
+# with or without modifications, as long as this notice is preserved.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
+# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+# PARTICULAR PURPOSE.
+
+@SET_MAKE@
+srcdir = @srcdir@
+top_srcdir = @top_srcdir@
+VPATH = @srcdir@
+pkgdatadir = $(datadir)/@PACKAGE@
+pkglibdir = $(libdir)/@PACKAGE@
+pkgincludedir = $(includedir)/@PACKAGE@
+top_builddir = .
+am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd
+INSTALL = @INSTALL@
+install_sh_DATA = $(install_sh) -c -m 644
+install_sh_PROGRAM = $(install_sh) -c
+install_sh_SCRIPT = $(install_sh) -c
+INSTALL_HEADER = $(INSTALL_DATA)
+transform = $(program_transform_name)
+NORMAL_INSTALL = :
+PRE_INSTALL = :
+POST_INSTALL = :
+NORMAL_UNINSTALL = :
+PRE_UNINSTALL = :
+POST_UNINSTALL = :
+subdir = .
+DIST_COMMON = README $(am__configure_deps) $(srcdir)/Makefile.am \
+	$(srcdir)/Makefile.in $(srcdir)/config.h.in \
+	$(top_srcdir)/configure AUTHORS COPYING ChangeLog INSTALL NEWS \
+	compile depcomp install-sh missing
+ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
+am__aclocal_m4_deps = $(top_srcdir)/acinclude.m4 \
+	$(top_srcdir)/configure.ac
+am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
+	$(ACLOCAL_M4)
+am__CONFIG_DISTCLEAN_FILES = config.status config.cache config.log \
+ configure.lineno configure.status.lineno
+mkinstalldirs = $(install_sh) -d
+CONFIG_HEADER = config.h
+CONFIG_CLEAN_FILES =
+SOURCES =
+DIST_SOURCES =
+RECURSIVE_TARGETS = all-recursive check-recursive dvi-recursive \
+	html-recursive info-recursive install-data-recursive \
+	install-exec-recursive install-info-recursive \
+	install-recursive installcheck-recursive installdirs-recursive \
+	pdf-recursive ps-recursive uninstall-info-recursive \
+	uninstall-recursive
+ETAGS = etags
+CTAGS = ctags
+DIST_SUBDIRS = $(SUBDIRS)
+DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
+distdir = $(PACKAGE)-$(VERSION)
+top_distdir = $(distdir)
+am__remove_distdir = \
+  { test ! -d $(distdir) \
+    || { find $(distdir) -type d ! -perm -200 -exec chmod u+w {} ';' \
+         && rm -fr $(distdir); }; }
+DIST_ARCHIVES = $(distdir).tar.gz
+GZIP_ENV = --best
+distuninstallcheck_listfiles = find . -type f -print
+distcleancheck_listfiles = find . -type f -print
+ACLOCAL = @ACLOCAL@
+AMDEP_FALSE = @AMDEP_FALSE@
+AMDEP_TRUE = @AMDEP_TRUE@
+AMTAR = @AMTAR@
+AUTOCONF = @AUTOCONF@
+AUTOHEADER = @AUTOHEADER@
+AUTOMAKE = @AUTOMAKE@
+AWK = @AWK@
+CC = @CC@
+CCDEPMODE = @CCDEPMODE@
+CFLAGS = @CFLAGS@
+CPP = @CPP@
+CPPFLAGS = @CPPFLAGS@
+CYGPATH_W = @CYGPATH_W@
+DEFS = @DEFS@
+DEPDIR = @DEPDIR@
+ECHO_C = @ECHO_C@
+ECHO_N = @ECHO_N@
+ECHO_T = @ECHO_T@
+EGREP = @EGREP@
+EXEEXT = @EXEEXT@
+INSTALL_DATA = @INSTALL_DATA@
+INSTALL_PROGRAM = @INSTALL_PROGRAM@
+INSTALL_SCRIPT = @INSTALL_SCRIPT@
+INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@
+LDFLAGS = @LDFLAGS@
+LIBOBJS = @LIBOBJS@
+LIBS = @LIBS@
+LTLIBOBJS = @LTLIBOBJS@
+MAKEINFO = @MAKEINFO@
+OBJEXT = @OBJEXT@
+PACKAGE = @PACKAGE@
+PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@
+PACKAGE_NAME = @PACKAGE_NAME@
+PACKAGE_STRING = @PACKAGE_STRING@
+PACKAGE_TARNAME = @PACKAGE_TARNAME@
+PACKAGE_VERSION = @PACKAGE_VERSION@
+PATH_SEPARATOR = @PATH_SEPARATOR@
+RANLIB = @RANLIB@
+SET_MAKE = @SET_MAKE@
+SHELL = @SHELL@
+STRIP = @STRIP@
+TCL_INCLUDE_SPEC = @TCL_INCLUDE_SPEC@
+TCL_LIB_SPEC = @TCL_LIB_SPEC@
+TK_LIBS = @TK_LIBS@
+TK_LIB_SPEC = @TK_LIB_SPEC@
+TK_PREFIX = @TK_PREFIX@
+TK_XINCLUDES = @TK_XINCLUDES@
+VERSION = @VERSION@
+ac_ct_CC = @ac_ct_CC@
+ac_ct_RANLIB = @ac_ct_RANLIB@
+ac_ct_STRIP = @ac_ct_STRIP@
+ac_prefix = @ac_prefix@
+am__fastdepCC_FALSE = @am__fastdepCC_FALSE@
+am__fastdepCC_TRUE = @am__fastdepCC_TRUE@
+am__include = @am__include@
+am__leading_dot = @am__leading_dot@
+am__quote = @am__quote@
+am__tar = @am__tar@
+am__untar = @am__untar@
+bindir = @bindir@
+build_alias = @build_alias@
+datadir = @datadir@
+exec_prefix = @exec_prefix@
+host_alias = @host_alias@
+includedir = @includedir@
+infodir = @infodir@
+install_sh = @install_sh@
+libdir = @libdir@
+libexecdir = @libexecdir@
+localstatedir = @localstatedir@
+mandir = @mandir@
+mkdir_p = @mkdir_p@
+oldincludedir = @oldincludedir@
+prefix = @prefix@
+program_transform_name = @program_transform_name@
+sbindir = @sbindir@
+sharedstatedir = @sharedstatedir@
+sysconfdir = @sysconfdir@
+target_alias = @target_alias@
+EXTRA_DIST = README ChangeLog COPYING INSTALL AUTHORS LICENSE doc dict include
+SUBDIRS = doc dict include lib src
+all: config.h
+	$(MAKE) $(AM_MAKEFLAGS) all-recursive
+
+.SUFFIXES:
+am--refresh:
+	@:
+$(srcdir)/Makefile.in:  $(srcdir)/Makefile.am  $(am__configure_deps)
+	@for dep in $?; do \
+	  case '$(am__configure_deps)' in \
+	    *$$dep*) \
+	      echo ' cd $(srcdir) && $(AUTOMAKE) --gnu '; \
+	      cd $(srcdir) && $(AUTOMAKE) --gnu  \
+		&& exit 0; \
+	      exit 1;; \
+	  esac; \
+	done; \
+	echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu  Makefile'; \
+	cd $(top_srcdir) && \
+	  $(AUTOMAKE) --gnu  Makefile
+.PRECIOUS: Makefile
+Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status
+	@case '$?' in \
+	  *config.status*) \
+	    echo ' $(SHELL) ./config.status'; \
+	    $(SHELL) ./config.status;; \
+	  *) \
+	    echo ' cd $(top_builddir) && $(SHELL) ./config.status $@ $(am__depfiles_maybe)'; \
+	    cd $(top_builddir) && $(SHELL) ./config.status $@ $(am__depfiles_maybe);; \
+	esac;
+
+$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES)
+	$(SHELL) ./config.status --recheck
+
+$(top_srcdir)/configure:  $(am__configure_deps)
+	cd $(srcdir) && $(AUTOCONF)
+$(ACLOCAL_M4):  $(am__aclocal_m4_deps)
+	cd $(srcdir) && $(ACLOCAL) $(ACLOCAL_AMFLAGS)
+
+config.h: stamp-h1
+	@if test ! -f $@; then \
+	  rm -f stamp-h1; \
+	  $(MAKE) stamp-h1; \
+	else :; fi
+
+stamp-h1: $(srcdir)/config.h.in $(top_builddir)/config.status
+	@rm -f stamp-h1
+	cd $(top_builddir) && $(SHELL) ./config.status config.h
+$(srcdir)/config.h.in:  $(am__configure_deps) 
+	cd $(top_srcdir) && $(AUTOHEADER)
+	rm -f stamp-h1
+	touch $@
+
+distclean-hdr:
+	-rm -f config.h stamp-h1
+uninstall-info-am:
+
+# This directory's subdirectories are mostly independent; you can cd
+# into them and run `make' without going through this Makefile.
+# To change the values of `make' variables: instead of editing Makefiles,
+# (1) if the variable is set in `config.status', edit `config.status'
+#     (which will cause the Makefiles to be regenerated when you run `make');
+# (2) otherwise, pass the desired values on the `make' command line.
+$(RECURSIVE_TARGETS):
+	@set fnord $$MAKEFLAGS; amf=$$2; \
+	dot_seen=no; \
+	target=`echo $@ | sed s/-recursive//`; \
+	list='$(SUBDIRS)'; for subdir in $$list; do \
+	  echo "Making $$target in $$subdir"; \
+	  if test "$$subdir" = "."; then \
+	    dot_seen=yes; \
+	    local_target="$$target-am"; \
+	  else \
+	    local_target="$$target"; \
+	  fi; \
+	  (cd $$subdir && $(MAKE) $(AM_MAKEFLAGS) $$local_target) \
+	   || case "$$amf" in *=*) exit 1;; *k*) fail=yes;; *) exit 1;; esac; \
+	done; \
+	if test "$$dot_seen" = "no"; then \
+	  $(MAKE) $(AM_MAKEFLAGS) "$$target-am" || exit 1; \
+	fi; test -z "$$fail"
+
+mostlyclean-recursive clean-recursive distclean-recursive \
+maintainer-clean-recursive:
+	@set fnord $$MAKEFLAGS; amf=$$2; \
+	dot_seen=no; \
+	case "$@" in \
+	  distclean-* | maintainer-clean-*) list='$(DIST_SUBDIRS)' ;; \
+	  *) list='$(SUBDIRS)' ;; \
+	esac; \
+	rev=''; for subdir in $$list; do \
+	  if test "$$subdir" = "."; then :; else \
+	    rev="$$subdir $$rev"; \
+	  fi; \
+	done; \
+	rev="$$rev ."; \
+	target=`echo $@ | sed s/-recursive//`; \
+	for subdir in $$rev; do \
+	  echo "Making $$target in $$subdir"; \
+	  if test "$$subdir" = "."; then \
+	    local_target="$$target-am"; \
+	  else \
+	    local_target="$$target"; \
+	  fi; \
+	  (cd $$subdir && $(MAKE) $(AM_MAKEFLAGS) $$local_target) \
+	   || case "$$amf" in *=*) exit 1;; *k*) fail=yes;; *) exit 1;; esac; \
+	done && test -z "$$fail"
+tags-recursive:
+	list='$(SUBDIRS)'; for subdir in $$list; do \
+	  test "$$subdir" = . || (cd $$subdir && $(MAKE) $(AM_MAKEFLAGS) tags); \
+	done
+ctags-recursive:
+	list='$(SUBDIRS)'; for subdir in $$list; do \
+	  test "$$subdir" = . || (cd $$subdir && $(MAKE) $(AM_MAKEFLAGS) ctags); \
+	done
+
+ID: $(HEADERS) $(SOURCES) $(LISP) $(TAGS_FILES)
+	list='$(SOURCES) $(HEADERS) $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	mkid -fID $$unique
+tags: TAGS
+
+TAGS: tags-recursive $(HEADERS) $(SOURCES) config.h.in $(TAGS_DEPENDENCIES) \
+		$(TAGS_FILES) $(LISP)
+	tags=; \
+	here=`pwd`; \
+	if ($(ETAGS) --etags-include --version) >/dev/null 2>&1; then \
+	  include_option=--etags-include; \
+	  empty_fix=.; \
+	else \
+	  include_option=--include; \
+	  empty_fix=; \
+	fi; \
+	list='$(SUBDIRS)'; for subdir in $$list; do \
+	  if test "$$subdir" = .; then :; else \
+	    test ! -f $$subdir/TAGS || \
+	      tags="$$tags $$include_option=$$here/$$subdir/TAGS"; \
+	  fi; \
+	done; \
+	list='$(SOURCES) $(HEADERS) config.h.in $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	if test -z "$(ETAGS_ARGS)$$tags$$unique"; then :; else \
+	  test -n "$$unique" || unique=$$empty_fix; \
+	  $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \
+	    $$tags $$unique; \
+	fi
+ctags: CTAGS
+CTAGS: ctags-recursive $(HEADERS) $(SOURCES) config.h.in $(TAGS_DEPENDENCIES) \
+		$(TAGS_FILES) $(LISP)
+	tags=; \
+	here=`pwd`; \
+	list='$(SOURCES) $(HEADERS) config.h.in $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	test -z "$(CTAGS_ARGS)$$tags$$unique" \
+	  || $(CTAGS) $(CTAGSFLAGS) $(AM_CTAGSFLAGS) $(CTAGS_ARGS) \
+	     $$tags $$unique
+
+GTAGS:
+	here=`$(am__cd) $(top_builddir) && pwd` \
+	  && cd $(top_srcdir) \
+	  && gtags -i $(GTAGS_ARGS) $$here
+
+distclean-tags:
+	-rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH tags
+
+distdir: $(DISTFILES)
+	$(am__remove_distdir)
+	mkdir $(distdir)
+	@srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; \
+	topsrcdirstrip=`echo "$(top_srcdir)" | sed 's|.|.|g'`; \
+	list='$(DISTFILES)'; for file in $$list; do \
+	  case $$file in \
+	    $(srcdir)/*) file=`echo "$$file" | sed "s|^$$srcdirstrip/||"`;; \
+	    $(top_srcdir)/*) file=`echo "$$file" | sed "s|^$$topsrcdirstrip/|$(top_builddir)/|"`;; \
+	  esac; \
+	  if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \
+	  dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \
+	  if test "$$dir" != "$$file" && test "$$dir" != "."; then \
+	    dir="/$$dir"; \
+	    $(mkdir_p) "$(distdir)$$dir"; \
+	  else \
+	    dir=''; \
+	  fi; \
+	  if test -d $$d/$$file; then \
+	    if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \
+	      cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \
+	    fi; \
+	    cp -pR $$d/$$file $(distdir)$$dir || exit 1; \
+	  else \
+	    test -f $(distdir)/$$file \
+	    || cp -p $$d/$$file $(distdir)/$$file \
+	    || exit 1; \
+	  fi; \
+	done
+	list='$(DIST_SUBDIRS)'; for subdir in $$list; do \
+	  if test "$$subdir" = .; then :; else \
+	    test -d "$(distdir)/$$subdir" \
+	    || $(mkdir_p) "$(distdir)/$$subdir" \
+	    || exit 1; \
+	    distdir=`$(am__cd) $(distdir) && pwd`; \
+	    top_distdir=`$(am__cd) $(top_distdir) && pwd`; \
+	    (cd $$subdir && \
+	      $(MAKE) $(AM_MAKEFLAGS) \
+	        top_distdir="$$top_distdir" \
+	        distdir="$$distdir/$$subdir" \
+	        distdir) \
+	      || exit 1; \
+	  fi; \
+	done
+	-find $(distdir) -type d ! -perm -777 -exec chmod a+rwx {} \; -o \
+	  ! -type d ! -perm -444 -links 1 -exec chmod a+r {} \; -o \
+	  ! -type d ! -perm -400 -exec chmod a+r {} \; -o \
+	  ! -type d ! -perm -444 -exec $(SHELL) $(install_sh) -c -m a+r {} {} \; \
+	|| chmod -R a+r $(distdir)
+dist-gzip: distdir
+	tardir=$(distdir) && $(am__tar) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).tar.gz
+	$(am__remove_distdir)
+
+dist-bzip2: distdir
+	tardir=$(distdir) && $(am__tar) | bzip2 -9 -c >$(distdir).tar.bz2
+	$(am__remove_distdir)
+
+dist-tarZ: distdir
+	tardir=$(distdir) && $(am__tar) | compress -c >$(distdir).tar.Z
+	$(am__remove_distdir)
+
+dist-shar: distdir
+	shar $(distdir) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).shar.gz
+	$(am__remove_distdir)
+
+dist-zip: distdir
+	-rm -f $(distdir).zip
+	zip -rq $(distdir).zip $(distdir)
+	$(am__remove_distdir)
+
+dist dist-all: distdir
+	tardir=$(distdir) && $(am__tar) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).tar.gz
+	$(am__remove_distdir)
+
+# This target untars the dist file and tries a VPATH configuration.  Then
+# it guarantees that the distribution is self-contained by making another
+# tarfile.
+distcheck: dist
+	case '$(DIST_ARCHIVES)' in \
+	*.tar.gz*) \
+	  GZIP=$(GZIP_ENV) gunzip -c $(distdir).tar.gz | $(am__untar) ;;\
+	*.tar.bz2*) \
+	  bunzip2 -c $(distdir).tar.bz2 | $(am__untar) ;;\
+	*.tar.Z*) \
+	  uncompress -c $(distdir).tar.Z | $(am__untar) ;;\
+	*.shar.gz*) \
+	  GZIP=$(GZIP_ENV) gunzip -c $(distdir).shar.gz | unshar ;;\
+	*.zip*) \
+	  unzip $(distdir).zip ;;\
+	esac
+	chmod -R a-w $(distdir); chmod a+w $(distdir)
+	mkdir $(distdir)/_build
+	mkdir $(distdir)/_inst
+	chmod a-w $(distdir)
+	dc_install_base=`$(am__cd) $(distdir)/_inst && pwd | sed -e 's,^[^:\\/]:[\\/],/,'` \
+	  && dc_destdir="$${TMPDIR-/tmp}/am-dc-$$$$/" \
+	  && cd $(distdir)/_build \
+	  && ../configure --srcdir=.. --prefix="$$dc_install_base" \
+	    $(DISTCHECK_CONFIGURE_FLAGS) \
+	  && $(MAKE) $(AM_MAKEFLAGS) \
+	  && $(MAKE) $(AM_MAKEFLAGS) dvi \
+	  && $(MAKE) $(AM_MAKEFLAGS) check \
+	  && $(MAKE) $(AM_MAKEFLAGS) install \
+	  && $(MAKE) $(AM_MAKEFLAGS) installcheck \
+	  && $(MAKE) $(AM_MAKEFLAGS) uninstall \
+	  && $(MAKE) $(AM_MAKEFLAGS) distuninstallcheck_dir="$$dc_install_base" \
+	        distuninstallcheck \
+	  && chmod -R a-w "$$dc_install_base" \
+	  && ({ \
+	       (cd ../.. && umask 077 && mkdir "$$dc_destdir") \
+	       && $(MAKE) $(AM_MAKEFLAGS) DESTDIR="$$dc_destdir" install \
+	       && $(MAKE) $(AM_MAKEFLAGS) DESTDIR="$$dc_destdir" uninstall \
+	       && $(MAKE) $(AM_MAKEFLAGS) DESTDIR="$$dc_destdir" \
+	            distuninstallcheck_dir="$$dc_destdir" distuninstallcheck; \
+	      } || { rm -rf "$$dc_destdir"; exit 1; }) \
+	  && rm -rf "$$dc_destdir" \
+	  && $(MAKE) $(AM_MAKEFLAGS) dist \
+	  && rm -rf $(DIST_ARCHIVES) \
+	  && $(MAKE) $(AM_MAKEFLAGS) distcleancheck
+	$(am__remove_distdir)
+	@(echo "$(distdir) archives ready for distribution: "; \
+	  list='$(DIST_ARCHIVES)'; for i in $$list; do echo $$i; done) | \
+	  sed -e '1{h;s/./=/g;p;x;}' -e '$${p;x;}'
+distuninstallcheck:
+	@cd $(distuninstallcheck_dir) \
+	&& test `$(distuninstallcheck_listfiles) | wc -l` -le 1 \
+	   || { echo "ERROR: files left after uninstall:" ; \
+	        if test -n "$(DESTDIR)"; then \
+	          echo "  (check DESTDIR support)"; \
+	        fi ; \
+	        $(distuninstallcheck_listfiles) ; \
+	        exit 1; } >&2
+distcleancheck: distclean
+	@if test '$(srcdir)' = . ; then \
+	  echo "ERROR: distcleancheck can only run from a VPATH build" ; \
+	  exit 1 ; \
+	fi
+	@test `$(distcleancheck_listfiles) | wc -l` -eq 0 \
+	  || { echo "ERROR: files left in build directory after distclean:" ; \
+	       $(distcleancheck_listfiles) ; \
+	       exit 1; } >&2
+check-am: all-am
+check: check-recursive
+all-am: Makefile config.h
+installdirs: installdirs-recursive
+installdirs-am:
+install: install-recursive
+install-exec: install-exec-recursive
+install-data: install-data-recursive
+uninstall: uninstall-recursive
+
+install-am: all-am
+	@$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am
+
+installcheck: installcheck-recursive
+install-strip:
+	$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
+	  install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
+	  `test -z '$(STRIP)' || \
+	    echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
+mostlyclean-generic:
+
+clean-generic:
+
+distclean-generic:
+	-test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES)
+
+maintainer-clean-generic:
+	@echo "This command is intended for maintainers to use"
+	@echo "it deletes files that may require special tools to rebuild."
+clean: clean-recursive
+
+clean-am: clean-generic mostlyclean-am
+
+distclean: distclean-recursive
+	-rm -f $(am__CONFIG_DISTCLEAN_FILES)
+	-rm -f Makefile
+distclean-am: clean-am distclean-generic distclean-hdr distclean-tags
+
+dvi: dvi-recursive
+
+dvi-am:
+
+html: html-recursive
+
+info: info-recursive
+
+info-am:
+
+install-data-am:
+
+install-exec-am:
+
+install-info: install-info-recursive
+
+install-man:
+
+installcheck-am:
+
+maintainer-clean: maintainer-clean-recursive
+	-rm -f $(am__CONFIG_DISTCLEAN_FILES)
+	-rm -rf $(top_srcdir)/autom4te.cache
+	-rm -f Makefile
+maintainer-clean-am: distclean-am maintainer-clean-generic
+
+mostlyclean: mostlyclean-recursive
+
+mostlyclean-am: mostlyclean-generic
+
+pdf: pdf-recursive
+
+pdf-am:
+
+ps: ps-recursive
+
+ps-am:
+
+uninstall-am: uninstall-info-am
+
+uninstall-info: uninstall-info-recursive
+
+.PHONY: $(RECURSIVE_TARGETS) CTAGS GTAGS all all-am am--refresh check \
+	check-am clean clean-generic clean-recursive ctags \
+	ctags-recursive dist dist-all dist-bzip2 dist-gzip dist-shar \
+	dist-tarZ dist-zip distcheck distclean distclean-generic \
+	distclean-hdr distclean-recursive distclean-tags \
+	distcleancheck distdir distuninstallcheck dvi dvi-am html \
+	html-am info info-am install install-am install-data \
+	install-data-am install-exec install-exec-am install-info \
+	install-info-am install-man install-strip installcheck \
+	installcheck-am installdirs installdirs-am maintainer-clean \
+	maintainer-clean-generic maintainer-clean-recursive \
+	mostlyclean mostlyclean-generic mostlyclean-recursive pdf \
+	pdf-am ps ps-am tags tags-recursive uninstall uninstall-am \
+	uninstall-info-am
+
+# Tell versions [3.59,3.63) of GNU make to not export all variables.
+# Otherwise a system limit (for SysV at least) may be exceeded.
+.NOEXPORT:

corpora/en/wordnet/README

@@ -0,0 +1,101 @@
+
+		This is the README file for WordNet 3.0
+
+1. About WordNet
+
+WordNet was developed at Princeton University's Cognitive Science
+Laboratory under the direction of George Miller, James S. McDonnell
+Distinguished University Professor of Psychology, Emeritus. Over the
+years many linguists, lexicographers, students, and software engineers
+have contributed to the project.
+
+WordNet is an online lexical reference system.  Word forms in WordNet
+are represented in their familiar orthography; word meanings are
+represented by synonym sets (synsets) - lists of synonymous word forms
+that are interchangeable in some context.  Two kinds of relations are
+recognized: lexical and semantic.  Lexical relations hold between word
+forms; semantic relations hold between word meanings.  
+
+To learn more about WordNet, the book "WordNet: An Electronic Lexical
+Database," containing an updated version of "Five Papers on WordNet"
+and additional papers by WordNet users, is available from MIT Press:
+
+    http://mitpress.mit.edu/book-home.tcl?isbn=026206197X
+
+2. The WordNet Web Site
+
+We maintain a Web site at:
+
+http://wordnet.princeton.edu
+
+Information about WordNet, access to our online interface, and the
+various WordNet packages that you can download are available from our
+web site.  All of the software documentation is available online, as
+well as a FAQ.  On this site we also have information about other
+applications that use WordNet. If you have an application that you
+would like included, please send e-mail to the above address.
+
+3. Contacting Us
+
+Ongoing deveopment work and WordNet related projects are done by a
+small group of researchers, lexicographers, and systems programmers.
+Since our resources are VERY limited, we request that you please
+confine correspondence to WordNet topics only.  Please check the
+documentation, FAQ, and other resources for the answer to your
+question or problem before contacting us.
+
+If you have trouble installing or downloading WordNet, have a bug to
+report, or any other problem, please refer to the online FAQ file
+first.  If you can heal thyself, please do so.  The FAQ will be
+updated over time.  And if you do find a previously unreported
+problem, please use our Bug Report Form:
+
+http://wordnet.princeton.edu/cgi-bin/bugsubmit.pl
+
+When reporting a problem, please be as specific as possible, stating
+the computer platform you are using, which interface you are using,
+and the exact error.  The more details you can provide, the more
+likely it is that you will get an answer. 
+
+There is a WordNet user discussion group mailing list that we invite
+our users to join.  Users use this list to ask questions of one
+another, announce extensions to WordNet that they've developed, and
+other topics of general usefulness to the user community.
+
+Information on joining the user discussion list, reporting bugs and other
+contact information is in found on our website at:
+
+http://wordnet.princeton.edu/contact
+
+4. Current Release
+
+WordNet Version 3.0 is the latest version available for download.  Two
+basic database packages are available - one for Windows and one for
+Unix platforms (including Mac OS X).  See the file ChangeLog (Unix) or
+CHANGES.txt (Windows) for a list of changes from previous versions.
+
+WordNet packages can either be downloaded from our web site via:
+
+http://wordnet.princeton.edu/obtain
+
+The Windows package is a self-extracting archive that installs itself
+when you double-click on it.
+
+Beginning with Version 2.1, we changed the Unix package to a GNU Autotools
+package.  The WordNet browser makes use of the open source Tcl and Tk
+packages. Many systems come with either or both pre-installed.  If
+your system doesn't (some systems have Tcl installed, but not Tk)
+Tcl/Tk can be downloaded from:
+
+http://www.tcl.tk/ 
+
+Tcl and Tk must be installed BEFORE you compile WordNet. You must also
+have a C compiler before installing Tcl/Tk or WordNet.  WordNet has
+been built and tested with the GNU gcc compiler.  This is
+pre-installed on most Unix systems, and can be downloaded from:
+
+http://gcc.gnu.org/
+
+See the file INSTALL for detailed WordNet installation instructions.
+
+

corpora/en/wordnet/acinclude.m4

@@ -0,0 +1,333 @@
+#------------------------------------------------------------------------
+# SC_PATH_TCLCONFIG --
+#
+#	Locate the tclConfig.sh file and perform a sanity check on
+#	the Tcl compile flags
+#
+# Arguments:
+#	none
+#
+# Results:
+#
+#	Adds the following arguments to configure:
+#		--with-tcl=...
+#
+#	Defines the following vars:
+#		TCL_BIN_DIR	Full path to the directory containing
+#				the tclConfig.sh file
+#------------------------------------------------------------------------
+
+AC_DEFUN(SC_PATH_TCLCONFIG, [
+    #
+    # Ok, lets find the tcl configuration
+    # First, look for one uninstalled.
+    # the alternative search directory is invoked by --with-tcl
+    #
+
+    if test x"${no_tcl}" = x ; then
+	# we reset no_tcl in case something fails here
+	no_tcl=true
+	AC_ARG_WITH(tcl, [  --with-tcl              directory containing tcl configuration (tclConfig.sh)], with_tclconfig=${withval})
+	AC_MSG_CHECKING([for Tcl configuration])
+	AC_CACHE_VAL(ac_cv_c_tclconfig,[
+
+	    # First check to see if --with-tcl was specified.
+	    if test x"${with_tclconfig}" != x ; then
+		if test -f "${with_tclconfig}/tclConfig.sh" ; then
+		    ac_cv_c_tclconfig=`(cd ${with_tclconfig}; pwd)`
+		else
+		    AC_MSG_ERROR([${with_tclconfig} directory doesn't contain tclConfig.sh])
+		fi
+	    fi
+
+	    # then check for a private Tcl installation
+	    if test x"${ac_cv_c_tclconfig}" = x ; then
+		for i in \
+			../tcl \
+			`ls -dr ../tcl[[8-9]].[[0-9]].[[0-9]]* 2>/dev/null` \
+			`ls -dr ../tcl[[8-9]].[[0-9]] 2>/dev/null` \
+			`ls -dr ../tcl[[8-9]].[[0-9]]* 2>/dev/null` \
+			../../tcl \
+			`ls -dr ../../tcl[[8-9]].[[0-9]].[[0-9]]* 2>/dev/null` \
+			`ls -dr ../../tcl[[8-9]].[[0-9]] 2>/dev/null` \
+			`ls -dr ../../tcl[[8-9]].[[0-9]]* 2>/dev/null` \
+			../../../tcl \
+			`ls -dr ../../../tcl[[8-9]].[[0-9]].[[0-9]]* 2>/dev/null` \
+			`ls -dr ../../../tcl[[8-9]].[[0-9]] 2>/dev/null` \
+			`ls -dr ../../../tcl[[8-9]].[[0-9]]* 2>/dev/null` ; do
+		    if test -f "$i/unix/tclConfig.sh" ; then
+			ac_cv_c_tclconfig=`(cd $i/unix; pwd)`
+			break
+		    fi
+		done
+	    fi
+
+	    # check in a few common install locations
+	    if test x"${ac_cv_c_tclconfig}" = x ; then
+		for i in `ls -d ${libdir} 2>/dev/null` \
+			`ls -d /usr/local/lib 2>/dev/null` \
+			`ls -d /usr/contrib/lib 2>/dev/null` \
+			`ls -d /usr/lib 2>/dev/null` \
+			`ls -d /usr/lib64 2>/dev/null` \
+			; do
+		    if test -f "$i/tclConfig.sh" ; then
+			ac_cv_c_tclconfig=`(cd $i; pwd)`
+			break
+		    fi
+		done
+	    fi
+
+	    # check in a few other private locations
+	    if test x"${ac_cv_c_tclconfig}" = x ; then
+		for i in \
+			${srcdir}/../tcl \
+			`ls -dr ${srcdir}/../tcl[[8-9]].[[0-9]].[[0-9]]* 2>/dev/null` \
+			`ls -dr ${srcdir}/../tcl[[8-9]].[[0-9]] 2>/dev/null` \
+			`ls -dr ${srcdir}/../tcl[[8-9]].[[0-9]]* 2>/dev/null` ; do
+		    if test -f "$i/unix/tclConfig.sh" ; then
+		    ac_cv_c_tclconfig=`(cd $i/unix; pwd)`
+		    break
+		fi
+		done
+	    fi
+	])
+
+	if test x"${ac_cv_c_tclconfig}" = x ; then
+	    TCL_BIN_DIR="# no Tcl configs found"
+	    AC_MSG_WARN(Can't find Tcl configuration definitions)
+	    exit 0
+	else
+	    no_tcl=
+	    TCL_BIN_DIR=${ac_cv_c_tclconfig}
+	    AC_MSG_RESULT(found $TCL_BIN_DIR/tclConfig.sh)
+	fi
+    fi
+])
+
+#------------------------------------------------------------------------
+# SC_PATH_TKCONFIG --
+#
+#	Locate the tkConfig.sh file
+#
+# Arguments:
+#	none
+#
+# Results:
+#
+#	Adds the following arguments to configure:
+#		--with-tk=...
+#
+#	Defines the following vars:
+#		TK_BIN_DIR	Full path to the directory containing
+#				the tkConfig.sh file
+#------------------------------------------------------------------------
+
+AC_DEFUN(SC_PATH_TKCONFIG, [
+    #
+    # Ok, lets find the tk configuration
+    # First, look for one uninstalled.
+    # the alternative search directory is invoked by --with-tk
+    #
+
+    if test x"${no_tk}" = x ; then
+	# we reset no_tk in case something fails here
+	no_tk=true
+	AC_ARG_WITH(tk, [  --with-tk               directory containing tk configuration (tkConfig.sh)], with_tkconfig=${withval})
+	AC_MSG_CHECKING([for Tk configuration])
+	AC_CACHE_VAL(ac_cv_c_tkconfig,[
+
+	    # First check to see if --with-tkconfig was specified.
+	    if test x"${with_tkconfig}" != x ; then
+		if test -f "${with_tkconfig}/tkConfig.sh" ; then
+		    ac_cv_c_tkconfig=`(cd ${with_tkconfig}; pwd)`
+		else
+		    AC_MSG_ERROR([${with_tkconfig} directory doesn't contain tkConfig.sh])
+		fi
+	    fi
+
+	    # then check for a private Tk library
+	    if test x"${ac_cv_c_tkconfig}" = x ; then
+		for i in \
+			../tk \
+			`ls -dr ../tk[[8-9]].[[0-9]].[[0-9]]* 2>/dev/null` \
+			`ls -dr ../tk[[8-9]].[[0-9]] 2>/dev/null` \
+			`ls -dr ../tk[[8-9]].[[0-9]]* 2>/dev/null` \
+			../../tk \
+			`ls -dr ../../tk[[8-9]].[[0-9]].[[0-9]]* 2>/dev/null` \
+			`ls -dr ../../tk[[8-9]].[[0-9]] 2>/dev/null` \
+			`ls -dr ../../tk[[8-9]].[[0-9]]* 2>/dev/null` \
+			../../../tk \
+			`ls -dr ../../../tk[[8-9]].[[0-9]].[[0-9]]* 2>/dev/null` \
+			`ls -dr ../../../tk[[8-9]].[[0-9]] 2>/dev/null` \
+			`ls -dr ../../../tk[[8-9]].[[0-9]]* 2>/dev/null` ; do
+		    if test -f "$i/unix/tkConfig.sh" ; then
+			ac_cv_c_tkconfig=`(cd $i/unix; pwd)`
+			break
+		    fi
+		done
+	    fi
+	    # check in a few common install locations
+	    if test x"${ac_cv_c_tkconfig}" = x ; then
+		for i in `ls -d ${libdir} 2>/dev/null` \
+			`ls -d /usr/local/lib 2>/dev/null` \
+			`ls -d /usr/contrib/lib 2>/dev/null` \
+			`ls -d /usr/lib 2>/dev/null` \
+			`ls -d /usr/lib64 2>/dev/null` \
+			; do
+		    if test -f "$i/tkConfig.sh" ; then
+			ac_cv_c_tkconfig=`(cd $i; pwd)`
+			break
+		    fi
+		done
+	    fi
+	    # check in a few other private locations
+	    if test x"${ac_cv_c_tkconfig}" = x ; then
+		for i in \
+			${srcdir}/../tk \
+			`ls -dr ${srcdir}/../tk[[8-9]].[[0-9]].[[0-9]]* 2>/dev/null` \
+			`ls -dr ${srcdir}/../tk[[8-9]].[[0-9]] 2>/dev/null` \
+			`ls -dr ${srcdir}/../tk[[8-9]].[[0-9]]* 2>/dev/null` ; do
+		    if test -f "$i/unix/tkConfig.sh" ; then
+			ac_cv_c_tkconfig=`(cd $i/unix; pwd)`
+			break
+		    fi
+		done
+	    fi
+	])
+	if test x"${ac_cv_c_tkconfig}" = x ; then
+	    TK_BIN_DIR="# no Tk configs found"
+	    AC_MSG_WARN(Can't find Tk configuration definitions)
+	    exit 0
+	else
+	    no_tk=
+	    TK_BIN_DIR=${ac_cv_c_tkconfig}
+	    AC_MSG_RESULT(found $TK_BIN_DIR/tkConfig.sh)
+	fi
+    fi
+
+])
+
+#------------------------------------------------------------------------
+# SC_LOAD_TCLCONFIG --
+#
+#	Load the tclConfig.sh file
+#
+# Arguments:
+#	
+#	Requires the following vars to be set:
+#		TCL_BIN_DIR
+#
+# Results:
+#
+#	Subst the following vars:
+#		TCL_BIN_DIR
+#		TCL_SRC_DIR
+#		TCL_LIB_FILE
+#
+#------------------------------------------------------------------------
+
+AC_DEFUN(SC_LOAD_TCLCONFIG, [
+    AC_MSG_CHECKING([for existence of $TCL_BIN_DIR/tclConfig.sh])
+
+    if test -f "$TCL_BIN_DIR/tclConfig.sh" ; then
+        AC_MSG_RESULT([loading])
+	. $TCL_BIN_DIR/tclConfig.sh
+    else
+        AC_MSG_RESULT([file not found])
+    fi
+
+    #
+    # If the TCL_BIN_DIR is the build directory (not the install directory),
+    # then set the common variable name to the value of the build variables.
+    # For example, the variable TCL_LIB_SPEC will be set to the value
+    # of TCL_BUILD_LIB_SPEC. An extension should make use of TCL_LIB_SPEC
+    # instead of TCL_BUILD_LIB_SPEC since it will work with both an
+    # installed and uninstalled version of Tcl.
+    #
+
+    if test -f $TCL_BIN_DIR/Makefile ; then
+        TCL_LIB_SPEC=${TCL_BUILD_LIB_SPEC}
+        TCL_STUB_LIB_SPEC=${TCL_BUILD_STUB_LIB_SPEC}
+        TCL_STUB_LIB_PATH=${TCL_BUILD_STUB_LIB_PATH}
+    fi
+
+    #
+    # eval is required to do the TCL_DBGX substitution
+    #
+
+    eval "TCL_LIB_FILE=\"${TCL_LIB_FILE}\""
+    eval "TCL_LIB_FLAG=\"${TCL_LIB_FLAG}\""
+    eval "TCL_LIB_SPEC=\"${TCL_LIB_SPEC}\""
+    eval "TCL_INCLUDE_SPEC=\"${TCL_INCLUDE_SPEC}\""
+
+    eval "TCL_STUB_LIB_FILE=\"${TCL_STUB_LIB_FILE}\""
+    eval "TCL_STUB_LIB_FLAG=\"${TCL_STUB_LIB_FLAG}\""
+    eval "TCL_STUB_LIB_SPEC=\"${TCL_STUB_LIB_SPEC}\""
+
+#    AC_SUBST(TCL_VERSION)
+#    AC_SUBST(TCL_BIN_DIR)
+#    AC_SUBST(TCL_SRC_DIR)
+
+#    AC_SUBST(TCL_LIB_FILE)
+#    AC_SUBST(TCL_LIB_FLAG)
+    AC_SUBST(TCL_LIB_SPEC)
+    AC_SUBST(TCL_INCLUDE_SPEC)
+
+#    AC_SUBST(TCL_STUB_LIB_FILE)
+#    AC_SUBST(TCL_STUB_LIB_FLAG)
+#    AC_SUBST(TCL_STUB_LIB_SPEC)
+])
+
+#------------------------------------------------------------------------
+# SC_LOAD_TKCONFIG --
+#
+#	Load the tkConfig.sh file
+#
+# Arguments:
+#	
+#	Requires the following vars to be set:
+#		TK_BIN_DIR
+#
+# Results:
+#
+#	Sets the following vars that should be in tkConfig.sh:
+#		TK_BIN_DIR
+#------------------------------------------------------------------------
+
+AC_DEFUN(SC_LOAD_TKCONFIG, [
+    AC_MSG_CHECKING([for existence of $TK_BIN_DIR/tkConfig.sh])
+
+    if test -f "$TK_BIN_DIR/tkConfig.sh" ; then
+        AC_MSG_RESULT([loading])
+	. $TK_BIN_DIR/tkConfig.sh
+    else
+        AC_MSG_RESULT([could not find $TK_BIN_DIR/tkConfig.sh])
+    fi
+
+    AC_SUBST(TK_LIB_SPEC)
+    AC_SUBST(TK_LIBS)
+    AC_SUBST(TK_XINCLUDES)
+    AC_SUBST(TK_PREFIX)
+
+#    AC_SUBST(TK_VERSION)
+#    AC_SUBST(TK_BIN_DIR)
+#    AC_SUBST(TK_SRC_DIR)
+#    AC_SUBST(TK_LIB_FILE)
+])
+
+dnl From Bruno Haible.
+
+AC_DEFUN([AC_LANGINFO_CODESET],
+[
+  AC_CACHE_CHECK([for nl_langinfo and CODESET], am_cv_langinfo_codeset,
+    [AC_TRY_LINK([#include <langinfo.h>],
+      [char* cs = nl_langinfo(CODESET);],
+      am_cv_langinfo_codeset=yes,
+      am_cv_langinfo_codeset=no)
+    ])
+  if test $am_cv_langinfo_codeset = yes; then
+    AC_DEFINE(HAVE_LANGINFO_CODESET, 1,
+      [Define if you have <langinfo.h> and nl_langinfo(CODESET).])
+  fi
+])
+

corpora/en/wordnet/compile

@@ -0,0 +1,136 @@
+#! /bin/sh
+# Wrapper for compilers which do not understand `-c -o'.
+
+scriptversion=2003-11-09.00
+
+# Copyright (C) 1999, 2000, 2003 Free Software Foundation, Inc.
+# Written by Tom Tromey <tromey@cygnus.com>.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2, or (at your option)
+# any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+
+# As a special exception to the GNU General Public License, if you
+# distribute this file as part of a program that contains a
+# configuration script generated by Autoconf, you may include it under
+# the same distribution terms that you use for the rest of that program.
+
+# This file is maintained in Automake, please report
+# bugs to <bug-automake@gnu.org> or send patches to
+# <automake-patches@gnu.org>.
+
+case $1 in
+  '')
+     echo "$0: No command.  Try \`$0 --help' for more information." 1>&2
+     exit 1;
+     ;;
+  -h | --h*)
+    cat <<\EOF
+Usage: compile [--help] [--version] PROGRAM [ARGS]
+
+Wrapper for compilers which do not understand `-c -o'.
+Remove `-o dest.o' from ARGS, run PROGRAM with the remaining
+arguments, and rename the output as expected.
+
+If you are trying to build a whole package this is not the
+right script to run: please start by reading the file `INSTALL'.
+
+Report bugs to <bug-automake@gnu.org>.
+EOF
+    exit 0
+    ;;
+  -v | --v*)
+    echo "compile $scriptversion"
+    exit 0
+    ;;
+esac
+
+
+prog=$1
+shift
+
+ofile=
+cfile=
+args=
+while test $# -gt 0; do
+  case "$1" in
+    -o)
+      # configure might choose to run compile as `compile cc -o foo foo.c'.
+      # So we do something ugly here.
+      ofile=$2
+      shift
+      case "$ofile" in
+	*.o | *.obj)
+	  ;;
+	*)
+	  args="$args -o $ofile"
+	  ofile=
+	  ;;
+      esac
+       ;;
+    *.c)
+      cfile=$1
+      args="$args $1"
+      ;;
+    *)
+      args="$args $1"
+      ;;
+  esac
+  shift
+done
+
+if test -z "$ofile" || test -z "$cfile"; then
+  # If no `-o' option was seen then we might have been invoked from a
+  # pattern rule where we don't need one.  That is ok -- this is a
+  # normal compilation that the losing compiler can handle.  If no
+  # `.c' file was seen then we are probably linking.  That is also
+  # ok.
+  exec "$prog" $args
+fi
+
+# Name of file we expect compiler to create.
+cofile=`echo $cfile | sed -e 's|^.*/||' -e 's/\.c$/.o/'`
+
+# Create the lock directory.
+# Note: use `[/.-]' here to ensure that we don't use the same name
+# that we are using for the .o file.  Also, base the name on the expected
+# object file name, since that is what matters with a parallel build.
+lockdir=`echo $cofile | sed -e 's|[/.-]|_|g'`.d
+while true; do
+  if mkdir $lockdir > /dev/null 2>&1; then
+    break
+  fi
+  sleep 1
+done
+# FIXME: race condition here if user kills between mkdir and trap.
+trap "rmdir $lockdir; exit 1" 1 2 15
+
+# Run the compile.
+"$prog" $args
+status=$?
+
+if test -f "$cofile"; then
+  mv "$cofile" "$ofile"
+fi
+
+rmdir $lockdir
+exit $status
+
+# Local Variables:
+# mode: shell-script
+# sh-indentation: 2
+# eval: (add-hook 'write-file-hooks 'time-stamp)
+# time-stamp-start: "scriptversion="
+# time-stamp-format: "%:y-%02m-%02d.%02H"
+# time-stamp-end: "$"
+# End:

corpora/en/wordnet/config.h.in

@@ -0,0 +1,86 @@
+/* config.h.in.  Generated from configure.ac by autoheader.  */
+
+/* Default installation prefix. */
+#undef DEFAULTPATH
+
+/* Define to 1 if you have the <inttypes.h> header file. */
+#undef HAVE_INTTYPES_H
+
+/* Define if you have <langinfo.h> and nl_langinfo(CODESET). */
+#undef HAVE_LANGINFO_CODESET
+
+/* Define to 1 if you have the <locale.h> header file. */
+#undef HAVE_LOCALE_H
+
+/* Define to 1 if your system has a GNU libc compatible `malloc' function, and
+   to 0 otherwise. */
+#undef HAVE_MALLOC
+
+/* Define to 1 if you have the <malloc.h> header file. */
+#undef HAVE_MALLOC_H
+
+/* Define to 1 if you have the <memory.h> header file. */
+#undef HAVE_MEMORY_H
+
+/* Define to 1 if you have the <stdint.h> header file. */
+#undef HAVE_STDINT_H
+
+/* Define to 1 if you have the <stdlib.h> header file. */
+#undef HAVE_STDLIB_H
+
+/* Define to 1 if you have the `strchr' function. */
+#undef HAVE_STRCHR
+
+/* Define to 1 if you have the `strdup' function. */
+#undef HAVE_STRDUP
+
+/* Define to 1 if you have the <strings.h> header file. */
+#undef HAVE_STRINGS_H
+
+/* Define to 1 if you have the <string.h> header file. */
+#undef HAVE_STRING_H
+
+/* Define to 1 if you have the `strrchr' function. */
+#undef HAVE_STRRCHR
+
+/* Define to 1 if you have the `strstr' function. */
+#undef HAVE_STRSTR
+
+/* Define to 1 if you have the `strtol' function. */
+#undef HAVE_STRTOL
+
+/* Define to 1 if you have the <sys/stat.h> header file. */
+#undef HAVE_SYS_STAT_H
+
+/* Define to 1 if you have the <sys/types.h> header file. */
+#undef HAVE_SYS_TYPES_H
+
+/* Define to 1 if you have the <unistd.h> header file. */
+#undef HAVE_UNISTD_H
+
+/* Name of package */
+#undef PACKAGE
+
+/* Define to the address where bug reports for this package should be sent. */
+#undef PACKAGE_BUGREPORT
+
+/* Define to the full name of this package. */
+#undef PACKAGE_NAME
+
+/* Define to the full name and version of this package. */
+#undef PACKAGE_STRING
+
+/* Define to the one symbol short name of this package. */
+#undef PACKAGE_TARNAME
+
+/* Define to the version of this package. */
+#undef PACKAGE_VERSION
+
+/* Define to 1 if you have the ANSI C header files. */
+#undef STDC_HEADERS
+
+/* Version number of package */
+#undef VERSION
+
+/* Define to rpl_malloc if the replacement function should be used. */
+#undef malloc

corpora/en/wordnet/configure.ac

@@ -0,0 +1,74 @@
+#                                               -*- Autoconf -*-
+# Process this file with autoconf to produce a configure script.
+
+AC_PREREQ(2.59)
+AC_INIT(WordNet, 3.0, [wordnet@princeton.edu], wordnet)
+AC_CONFIG_SRCDIR([config.h.in])
+AC_CONFIG_HEADER([config.h])
+
+# Checks for programs.
+AC_PROG_CC
+AC_PROG_RANLIB
+AC_PROG_INSTALL
+
+# Checks for header files.
+AC_HEADER_STDC
+AC_CHECK_HEADERS([locale.h malloc.h stdlib.h string.h])
+
+# Checks for typedefs, structures, and compiler characteristics.
+
+# Checks for library functions.
+AC_FUNC_MALLOC
+AC_CHECK_FUNCS([strchr strdup strrchr strstr strtol])
+
+# Set HAVE_LANGINFO_CODESET if nl_langinfo is found
+
+AC_LANGINFO_CODESET
+
+AM_INIT_AUTOMAKE(WordNet, 3.0)
+
+SC_PATH_TCLCONFIG
+SC_PATH_TKCONFIG
+SC_LOAD_TCLCONFIG
+SC_LOAD_TKCONFIG
+
+# Set default installation prefix.
+AC_PREFIX_DEFAULT([/usr/local/WordNet-3.0])
+ac_prefix=$prefix
+if test "x$ac_prefix" = "xNONE"; then
+    ac_prefix=$ac_default_prefix
+fi
+AC_SUBST(ac_prefix)
+AH_TEMPLATE([DEFAULTPATH],[The default search path for WordNet data files])
+AC_DEFINE_UNQUOTED(DEFAULTPATH, ["$ac_prefix/dict"], [Default installation prefix.])
+
+#AC_DEFINE_UNQUOTED(DEFAULTPATH,"${prefix}/dict")
+
+# This doesn't do anything
+AC_CONFIG_COMMANDS([default])
+
+AC_CONFIG_FILES(Makefile dict/Makefile doc/Makefile doc/html/Makefile doc/man/Makefile doc/pdf/Makefile doc/ps/Makefile include/Makefile include/tk/Makefile
+src/Makefile lib/Makefile lib/wnres/Makefile)
+
+AC_OUTPUT
+
+AC_MSG_RESULT(
+[
+WordNet is now configured
+
+  Installation directory:               ${prefix}
+
+  To build and install WordNet:
+
+    make
+    make install
+
+  To run, environment variables should be set as follows:
+
+    PATH - include ${bindir}
+    WNHOME - if not using default installation location, set to ${prefix}
+
+    See INSTALL file for details and additional environment variables
+    which may need to be set on your system.
+
+])

corpora/en/wordnet/depcomp

@@ -0,0 +1,522 @@
+#! /bin/sh
+# depcomp - compile a program generating dependencies as side-effects
+
+scriptversion=2004-05-31.23
+
+# Copyright (C) 1999, 2000, 2003, 2004 Free Software Foundation, Inc.
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2, or (at your option)
+# any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
+# 02111-1307, USA.
+
+# As a special exception to the GNU General Public License, if you
+# distribute this file as part of a program that contains a
+# configuration script generated by Autoconf, you may include it under
+# the same distribution terms that you use for the rest of that program.
+
+# Originally written by Alexandre Oliva <oliva@dcc.unicamp.br>.
+
+case $1 in
+  '')
+     echo "$0: No command.  Try \`$0 --help' for more information." 1>&2
+     exit 1;
+     ;;
+  -h | --h*)
+    cat <<\EOF
+Usage: depcomp [--help] [--version] PROGRAM [ARGS]
+
+Run PROGRAMS ARGS to compile a file, generating dependencies
+as side-effects.
+
+Environment variables:
+  depmode     Dependency tracking mode.
+  source      Source file read by `PROGRAMS ARGS'.
+  object      Object file output by `PROGRAMS ARGS'.
+  DEPDIR      directory where to store dependencies.
+  depfile     Dependency file to output.
+  tmpdepfile  Temporary file to use when outputing dependencies.
+  libtool     Whether libtool is used (yes/no).
+
+Report bugs to <bug-automake@gnu.org>.
+EOF
+    exit 0
+    ;;
+  -v | --v*)
+    echo "depcomp $scriptversion"
+    exit 0
+    ;;
+esac
+
+if test -z "$depmode" || test -z "$source" || test -z "$object"; then
+  echo "depcomp: Variables source, object and depmode must be set" 1>&2
+  exit 1
+fi
+
+# Dependencies for sub/bar.o or sub/bar.obj go into sub/.deps/bar.Po.
+depfile=${depfile-`echo "$object" |
+  sed 's|[^\\/]*$|'${DEPDIR-.deps}'/&|;s|\.\([^.]*\)$|.P\1|;s|Pobj$|Po|'`}
+tmpdepfile=${tmpdepfile-`echo "$depfile" | sed 's/\.\([^.]*\)$/.T\1/'`}
+
+rm -f "$tmpdepfile"
+
+# Some modes work just like other modes, but use different flags.  We
+# parameterize here, but still list the modes in the big case below,
+# to make depend.m4 easier to write.  Note that we *cannot* use a case
+# here, because this file can only contain one case statement.
+if test "$depmode" = hp; then
+  # HP compiler uses -M and no extra arg.
+  gccflag=-M
+  depmode=gcc
+fi
+
+if test "$depmode" = dashXmstdout; then
+   # This is just like dashmstdout with a different argument.
+   dashmflag=-xM
+   depmode=dashmstdout
+fi
+
+case "$depmode" in
+gcc3)
+## gcc 3 implements dependency tracking that does exactly what
+## we want.  Yay!  Note: for some reason libtool 1.4 doesn't like
+## it if -MD -MP comes after the -MF stuff.  Hmm.
+  "$@" -MT "$object" -MD -MP -MF "$tmpdepfile"
+  stat=$?
+  if test $stat -eq 0; then :
+  else
+    rm -f "$tmpdepfile"
+    exit $stat
+  fi
+  mv "$tmpdepfile" "$depfile"
+  ;;
+
+gcc)
+## There are various ways to get dependency output from gcc.  Here's
+## why we pick this rather obscure method:
+## - Don't want to use -MD because we'd like the dependencies to end
+##   up in a subdir.  Having to rename by hand is ugly.
+##   (We might end up doing this anyway to support other compilers.)
+## - The DEPENDENCIES_OUTPUT environment variable makes gcc act like
+##   -MM, not -M (despite what the docs say).
+## - Using -M directly means running the compiler twice (even worse
+##   than renaming).
+  if test -z "$gccflag"; then
+    gccflag=-MD,
+  fi
+  "$@" -Wp,"$gccflag$tmpdepfile"
+  stat=$?
+  if test $stat -eq 0; then :
+  else
+    rm -f "$tmpdepfile"
+    exit $stat
+  fi
+  rm -f "$depfile"
+  echo "$object : \\" > "$depfile"
+  alpha=ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz
+## The second -e expression handles DOS-style file names with drive letters.
+  sed -e 's/^[^:]*: / /' \
+      -e 's/^['$alpha']:\/[^:]*: / /' < "$tmpdepfile" >> "$depfile"
+## This next piece of magic avoids the `deleted header file' problem.
+## The problem is that when a header file which appears in a .P file
+## is deleted, the dependency causes make to die (because there is
+## typically no way to rebuild the header).  We avoid this by adding
+## dummy dependencies for each header file.  Too bad gcc doesn't do
+## this for us directly.
+  tr ' ' '
+' < "$tmpdepfile" |
+## Some versions of gcc put a space before the `:'.  On the theory
+## that the space means something, we add a space to the output as
+## well.
+## Some versions of the HPUX 10.20 sed can't process this invocation
+## correctly.  Breaking it into two sed invocations is a workaround.
+    sed -e 's/^\\$//' -e '/^$/d' -e '/:$/d' | sed -e 's/$/ :/' >> "$depfile"
+  rm -f "$tmpdepfile"
+  ;;
+
+hp)
+  # This case exists only to let depend.m4 do its work.  It works by
+  # looking at the text of this script.  This case will never be run,
+  # since it is checked for above.
+  exit 1
+  ;;
+
+sgi)
+  if test "$libtool" = yes; then
+    "$@" "-Wp,-MDupdate,$tmpdepfile"
+  else
+    "$@" -MDupdate "$tmpdepfile"
+  fi
+  stat=$?
+  if test $stat -eq 0; then :
+  else
+    rm -f "$tmpdepfile"
+    exit $stat
+  fi
+  rm -f "$depfile"
+
+  if test -f "$tmpdepfile"; then  # yes, the sourcefile depend on other files
+    echo "$object : \\" > "$depfile"
+
+    # Clip off the initial element (the dependent).  Don't try to be
+    # clever and replace this with sed code, as IRIX sed won't handle
+    # lines with more than a fixed number of characters (4096 in
+    # IRIX 6.2 sed, 8192 in IRIX 6.5).  We also remove comment lines;
+    # the IRIX cc adds comments like `#:fec' to the end of the
+    # dependency line.
+    tr ' ' '
+' < "$tmpdepfile" \
+    | sed -e 's/^.*\.o://' -e 's/#.*$//' -e '/^$/ d' | \
+    tr '
+' ' ' >> $depfile
+    echo >> $depfile
+
+    # The second pass generates a dummy entry for each header file.
+    tr ' ' '
+' < "$tmpdepfile" \
+   | sed -e 's/^.*\.o://' -e 's/#.*$//' -e '/^$/ d' -e 's/$/:/' \
+   >> $depfile
+  else
+    # The sourcefile does not contain any dependencies, so just
+    # store a dummy comment line, to avoid errors with the Makefile
+    # "include basename.Plo" scheme.
+    echo "#dummy" > "$depfile"
+  fi
+  rm -f "$tmpdepfile"
+  ;;
+
+aix)
+  # The C for AIX Compiler uses -M and outputs the dependencies
+  # in a .u file.  In older versions, this file always lives in the
+  # current directory.  Also, the AIX compiler puts `$object:' at the
+  # start of each line; $object doesn't have directory information.
+  # Version 6 uses the directory in both cases.
+  stripped=`echo "$object" | sed 's/\(.*\)\..*$/\1/'`
+  tmpdepfile="$stripped.u"
+  if test "$libtool" = yes; then
+    "$@" -Wc,-M
+  else
+    "$@" -M
+  fi
+  stat=$?
+
+  if test -f "$tmpdepfile"; then :
+  else
+    stripped=`echo "$stripped" | sed 's,^.*/,,'`
+    tmpdepfile="$stripped.u"
+  fi
+
+  if test $stat -eq 0; then :
+  else
+    rm -f "$tmpdepfile"
+    exit $stat
+  fi
+
+  if test -f "$tmpdepfile"; then
+    outname="$stripped.o"
+    # Each line is of the form `foo.o: dependent.h'.
+    # Do two passes, one to just change these to
+    # `$object: dependent.h' and one to simply `dependent.h:'.
+    sed -e "s,^$outname:,$object :," < "$tmpdepfile" > "$depfile"
+    sed -e "s,^$outname: \(.*\)$,\1:," < "$tmpdepfile" >> "$depfile"
+  else
+    # The sourcefile does not contain any dependencies, so just
+    # store a dummy comment line, to avoid errors with the Makefile
+    # "include basename.Plo" scheme.
+    echo "#dummy" > "$depfile"
+  fi
+  rm -f "$tmpdepfile"
+  ;;
+
+icc)
+  # Intel's C compiler understands `-MD -MF file'.  However on
+  #    icc -MD -MF foo.d -c -o sub/foo.o sub/foo.c
+  # ICC 7.0 will fill foo.d with something like
+  #    foo.o: sub/foo.c
+  #    foo.o: sub/foo.h
+  # which is wrong.  We want:
+  #    sub/foo.o: sub/foo.c
+  #    sub/foo.o: sub/foo.h
+  #    sub/foo.c:
+  #    sub/foo.h:
+  # ICC 7.1 will output
+  #    foo.o: sub/foo.c sub/foo.h
+  # and will wrap long lines using \ :
+  #    foo.o: sub/foo.c ... \
+  #     sub/foo.h ... \
+  #     ...
+
+  "$@" -MD -MF "$tmpdepfile"
+  stat=$?
+  if test $stat -eq 0; then :
+  else
+    rm -f "$tmpdepfile"
+    exit $stat
+  fi
+  rm -f "$depfile"
+  # Each line is of the form `foo.o: dependent.h',
+  # or `foo.o: dep1.h dep2.h \', or ` dep3.h dep4.h \'.
+  # Do two passes, one to just change these to
+  # `$object: dependent.h' and one to simply `dependent.h:'.
+  sed "s,^[^:]*:,$object :," < "$tmpdepfile" > "$depfile"
+  # Some versions of the HPUX 10.20 sed can't process this invocation
+  # correctly.  Breaking it into two sed invocations is a workaround.
+  sed 's,^[^:]*: \(.*\)$,\1,;s/^\\$//;/^$/d;/:$/d' < "$tmpdepfile" |
+    sed -e 's/$/ :/' >> "$depfile"
+  rm -f "$tmpdepfile"
+  ;;
+
+tru64)
+   # The Tru64 compiler uses -MD to generate dependencies as a side
+   # effect.  `cc -MD -o foo.o ...' puts the dependencies into `foo.o.d'.
+   # At least on Alpha/Redhat 6.1, Compaq CCC V6.2-504 seems to put
+   # dependencies in `foo.d' instead, so we check for that too.
+   # Subdirectories are respected.
+   dir=`echo "$object" | sed -e 's|/[^/]*$|/|'`
+   test "x$dir" = "x$object" && dir=
+   base=`echo "$object" | sed -e 's|^.*/||' -e 's/\.o$//' -e 's/\.lo$//'`
+
+   if test "$libtool" = yes; then
+      # Dependencies are output in .lo.d with libtool 1.4.
+      # With libtool 1.5 they are output both in $dir.libs/$base.o.d
+      # and in $dir.libs/$base.o.d and $dir$base.o.d.  We process the
+      # latter, because the former will be cleaned when $dir.libs is
+      # erased.
+      tmpdepfile1="$dir.libs/$base.lo.d"
+      tmpdepfile2="$dir$base.o.d"
+      tmpdepfile3="$dir.libs/$base.d"
+      "$@" -Wc,-MD
+   else
+      tmpdepfile1="$dir$base.o.d"
+      tmpdepfile2="$dir$base.d"
+      tmpdepfile3="$dir$base.d"
+      "$@" -MD
+   fi
+
+   stat=$?
+   if test $stat -eq 0; then :
+   else
+      rm -f "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3"
+      exit $stat
+   fi
+
+   if test -f "$tmpdepfile1"; then
+      tmpdepfile="$tmpdepfile1"
+   elif test -f "$tmpdepfile2"; then
+      tmpdepfile="$tmpdepfile2"
+   else
+      tmpdepfile="$tmpdepfile3"
+   fi
+   if test -f "$tmpdepfile"; then
+      sed -e "s,^.*\.[a-z]*:,$object:," < "$tmpdepfile" > "$depfile"
+      # That's a tab and a space in the [].
+      sed -e 's,^.*\.[a-z]*:[	 ]*,,' -e 's,$,:,' < "$tmpdepfile" >> "$depfile"
+   else
+      echo "#dummy" > "$depfile"
+   fi
+   rm -f "$tmpdepfile"
+   ;;
+
+#nosideeffect)
+  # This comment above is used by automake to tell side-effect
+  # dependency tracking mechanisms from slower ones.
+
+dashmstdout)
+  # Important note: in order to support this mode, a compiler *must*
+  # always write the preprocessed file to stdout, regardless of -o.
+  "$@" || exit $?
+
+  # Remove the call to Libtool.
+  if test "$libtool" = yes; then
+    while test $1 != '--mode=compile'; do
+      shift
+    done
+    shift
+  fi
+
+  # Remove `-o $object'.
+  IFS=" "
+  for arg
+  do
+    case $arg in
+    -o)
+      shift
+      ;;
+    $object)
+      shift
+      ;;
+    *)
+      set fnord "$@" "$arg"
+      shift # fnord
+      shift # $arg
+      ;;
+    esac
+  done
+
+  test -z "$dashmflag" && dashmflag=-M
+  # Require at least two characters before searching for `:'
+  # in the target name.  This is to cope with DOS-style filenames:
+  # a dependency such as `c:/foo/bar' could be seen as target `c' otherwise.
+  "$@" $dashmflag |
+    sed 's:^[  ]*[^: ][^:][^:]*\:[    ]*:'"$object"'\: :' > "$tmpdepfile"
+  rm -f "$depfile"
+  cat < "$tmpdepfile" > "$depfile"
+  tr ' ' '
+' < "$tmpdepfile" | \
+## Some versions of the HPUX 10.20 sed can't process this invocation
+## correctly.  Breaking it into two sed invocations is a workaround.
+    sed -e 's/^\\$//' -e '/^$/d' -e '/:$/d' | sed -e 's/$/ :/' >> "$depfile"
+  rm -f "$tmpdepfile"
+  ;;
+
+dashXmstdout)
+  # This case only exists to satisfy depend.m4.  It is never actually
+  # run, as this mode is specially recognized in the preamble.
+  exit 1
+  ;;
+
+makedepend)
+  "$@" || exit $?
+  # Remove any Libtool call
+  if test "$libtool" = yes; then
+    while test $1 != '--mode=compile'; do
+      shift
+    done
+    shift
+  fi
+  # X makedepend
+  shift
+  cleared=no
+  for arg in "$@"; do
+    case $cleared in
+    no)
+      set ""; shift
+      cleared=yes ;;
+    esac
+    case "$arg" in
+    -D*|-I*)
+      set fnord "$@" "$arg"; shift ;;
+    # Strip any option that makedepend may not understand.  Remove
+    # the object too, otherwise makedepend will parse it as a source file.
+    -*|$object)
+      ;;
+    *)
+      set fnord "$@" "$arg"; shift ;;
+    esac
+  done
+  obj_suffix="`echo $object | sed 's/^.*\././'`"
+  touch "$tmpdepfile"
+  ${MAKEDEPEND-makedepend} -o"$obj_suffix" -f"$tmpdepfile" "$@"
+  rm -f "$depfile"
+  cat < "$tmpdepfile" > "$depfile"
+  sed '1,2d' "$tmpdepfile" | tr ' ' '
+' | \
+## Some versions of the HPUX 10.20 sed can't process this invocation
+## correctly.  Breaking it into two sed invocations is a workaround.
+    sed -e 's/^\\$//' -e '/^$/d' -e '/:$/d' | sed -e 's/$/ :/' >> "$depfile"
+  rm -f "$tmpdepfile" "$tmpdepfile".bak
+  ;;
+
+cpp)
+  # Important note: in order to support this mode, a compiler *must*
+  # always write the preprocessed file to stdout.
+  "$@" || exit $?
+
+  # Remove the call to Libtool.
+  if test "$libtool" = yes; then
+    while test $1 != '--mode=compile'; do
+      shift
+    done
+    shift
+  fi
+
+  # Remove `-o $object'.
+  IFS=" "
+  for arg
+  do
+    case $arg in
+    -o)
+      shift
+      ;;
+    $object)
+      shift
+      ;;
+    *)
+      set fnord "$@" "$arg"
+      shift # fnord
+      shift # $arg
+      ;;
+    esac
+  done
+
+  "$@" -E |
+    sed -n '/^# [0-9][0-9]* "\([^"]*\)".*/ s:: \1 \\:p' |
+    sed '$ s: \\$::' > "$tmpdepfile"
+  rm -f "$depfile"
+  echo "$object : \\" > "$depfile"
+  cat < "$tmpdepfile" >> "$depfile"
+  sed < "$tmpdepfile" '/^$/d;s/^ //;s/ \\$//;s/$/ :/' >> "$depfile"
+  rm -f "$tmpdepfile"
+  ;;
+
+msvisualcpp)
+  # Important note: in order to support this mode, a compiler *must*
+  # always write the preprocessed file to stdout, regardless of -o,
+  # because we must use -o when running libtool.
+  "$@" || exit $?
+  IFS=" "
+  for arg
+  do
+    case "$arg" in
+    "-Gm"|"/Gm"|"-Gi"|"/Gi"|"-ZI"|"/ZI")
+	set fnord "$@"
+	shift
+	shift
+	;;
+    *)
+	set fnord "$@" "$arg"
+	shift
+	shift
+	;;
+    esac
+  done
+  "$@" -E |
+  sed -n '/^#line [0-9][0-9]* "\([^"]*\)"/ s::echo "`cygpath -u \\"\1\\"`":p' | sort | uniq > "$tmpdepfile"
+  rm -f "$depfile"
+  echo "$object : \\" > "$depfile"
+  . "$tmpdepfile" | sed 's% %\\ %g' | sed -n '/^\(.*\)$/ s::	\1 \\:p' >> "$depfile"
+  echo "	" >> "$depfile"
+  . "$tmpdepfile" | sed 's% %\\ %g' | sed -n '/^\(.*\)$/ s::\1\::p' >> "$depfile"
+  rm -f "$tmpdepfile"
+  ;;
+
+none)
+  exec "$@"
+  ;;
+
+*)
+  echo "Unknown depmode $depmode" 1>&2
+  exit 1
+  ;;
+esac
+
+exit 0
+
+# Local Variables:
+# mode: shell-script
+# sh-indentation: 2
+# eval: (add-hook 'write-file-hooks 'time-stamp)
+# time-stamp-start: "scriptversion="
+# time-stamp-format: "%:y-%02m-%02d.%02H"
+# time-stamp-end: "$"
+# End:

corpora/en/wordnet/dict/Makefile

@@ -0,0 +1,314 @@
+# Makefile.in generated by automake 1.9 from Makefile.am.
+# dict/Makefile.  Generated from Makefile.in by configure.
+
+# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
+# 2003, 2004  Free Software Foundation, Inc.
+# This Makefile.in is free software; the Free Software Foundation
+# gives unlimited permission to copy and/or distribute it,
+# with or without modifications, as long as this notice is preserved.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
+# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+# PARTICULAR PURPOSE.
+
+
+
+srcdir = .
+top_srcdir = ..
+
+pkgdatadir = $(datadir)/WordNet
+pkglibdir = $(libdir)/WordNet
+pkgincludedir = $(includedir)/WordNet
+top_builddir = ..
+am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd
+INSTALL = /usr/csl/bin/install -c
+install_sh_DATA = $(install_sh) -c -m 644
+install_sh_PROGRAM = $(install_sh) -c
+install_sh_SCRIPT = $(install_sh) -c
+INSTALL_HEADER = $(INSTALL_DATA)
+transform = $(program_transform_name)
+NORMAL_INSTALL = :
+PRE_INSTALL = :
+POST_INSTALL = :
+NORMAL_UNINSTALL = :
+PRE_UNINSTALL = :
+POST_UNINSTALL = :
+subdir = dict
+DIST_COMMON = $(srcdir)/Makefile.am $(srcdir)/Makefile.in
+ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
+am__aclocal_m4_deps = $(top_srcdir)/acinclude.m4 \
+	$(top_srcdir)/configure.ac
+am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
+	$(ACLOCAL_M4)
+mkinstalldirs = $(install_sh) -d
+CONFIG_HEADER = $(top_builddir)/config.h
+CONFIG_CLEAN_FILES =
+SOURCES =
+DIST_SOURCES =
+am__vpath_adj_setup = srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`;
+am__vpath_adj = case $$p in \
+    $(srcdir)/*) f=`echo "$$p" | sed "s|^$$srcdirstrip/||"`;; \
+    *) f=$$p;; \
+  esac;
+am__strip_dir = `echo $$p | sed -e 's|^.*/||'`;
+am__installdirs = "$(DESTDIR)$(dictdir)"
+dictDATA_INSTALL = $(INSTALL_DATA)
+DATA = $(dict_DATA)
+DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
+ACLOCAL = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run aclocal-1.9
+AMDEP_FALSE = #
+AMDEP_TRUE = 
+AMTAR = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run tar
+AUTOCONF = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run autoconf
+AUTOHEADER = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run autoheader
+AUTOMAKE = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run automake-1.9
+AWK = nawk
+CC = gcc
+CCDEPMODE = depmode=gcc3
+CFLAGS = -g -O2
+CPP = gcc -E
+CPPFLAGS = 
+CYGPATH_W = echo
+DEFS = -DHAVE_CONFIG_H
+DEPDIR = .deps
+ECHO_C = 
+ECHO_N = -n
+ECHO_T = 
+EGREP = egrep
+EXEEXT = 
+INSTALL_DATA = ${INSTALL} -m 644
+INSTALL_PROGRAM = ${INSTALL}
+INSTALL_SCRIPT = ${INSTALL}
+INSTALL_STRIP_PROGRAM = ${SHELL} $(install_sh) -c -s
+LDFLAGS = 
+LIBOBJS = 
+LIBS = 
+LTLIBOBJS = 
+MAKEINFO = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run makeinfo
+OBJEXT = o
+PACKAGE = WordNet
+PACKAGE_BUGREPORT = wordnet@princeton.edu
+PACKAGE_NAME = WordNet
+PACKAGE_STRING = WordNet 3.0
+PACKAGE_TARNAME = wordnet
+PACKAGE_VERSION = 3.0
+PATH_SEPARATOR = :
+RANLIB = ranlib
+SET_MAKE = 
+SHELL = /bin/bash
+STRIP = 
+TCL_INCLUDE_SPEC = -I/usr/csl/include
+TCL_LIB_SPEC = -L/usr/csl/lib -ltcl8.4
+TK_LIBS = -L/usr/openwin/lib -lX11 -ldl  -lpthread -lsocket -lnsl -lm
+TK_LIB_SPEC = -L/usr/csl/lib -ltk8.4
+TK_PREFIX = /usr/csl
+TK_XINCLUDES = -I/usr/openwin/include
+VERSION = 3.0
+ac_ct_CC = gcc
+ac_ct_RANLIB = ranlib
+ac_ct_STRIP = 
+ac_prefix = /usr/local/WordNet-3.0
+am__fastdepCC_FALSE = #
+am__fastdepCC_TRUE = 
+am__include = include
+am__leading_dot = .
+am__quote = 
+am__tar = ${AMTAR} chof - "$$tardir"
+am__untar = ${AMTAR} xf -
+bindir = ${exec_prefix}/bin
+build_alias = 
+datadir = ${prefix}/share
+exec_prefix = ${prefix}
+host_alias = 
+includedir = ${prefix}/include
+infodir = ${prefix}/info
+install_sh = /people/wn/src/Release/3.0/Unix/install-sh
+libdir = ${exec_prefix}/lib
+libexecdir = ${exec_prefix}/libexec
+localstatedir = ${prefix}/var
+mandir = ${prefix}/man
+mkdir_p = $(install_sh) -d
+oldincludedir = /usr/include
+prefix = /usr/local/WordNet-3.0
+program_transform_name = s,x,x,
+sbindir = ${exec_prefix}/sbin
+sharedstatedir = ${prefix}/com
+sysconfdir = ${prefix}/etc
+target_alias = 
+dictdir = $(prefix)/dict
+dict_DATA = adj.exc adv.exc cntlist cntlist.rev data.adj data.adv data.noun data.verb frames.vrb index.adj index.adv index.noun index.sense index.verb log.grind.3.0 noun.exc sentidx.vrb sents.vrb verb.Framestext verb.exc lexnames
+all: all-am
+
+.SUFFIXES:
+$(srcdir)/Makefile.in:  $(srcdir)/Makefile.am  $(am__configure_deps)
+	@for dep in $?; do \
+	  case '$(am__configure_deps)' in \
+	    *$$dep*) \
+	      cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh \
+		&& exit 0; \
+	      exit 1;; \
+	  esac; \
+	done; \
+	echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu  dict/Makefile'; \
+	cd $(top_srcdir) && \
+	  $(AUTOMAKE) --gnu  dict/Makefile
+.PRECIOUS: Makefile
+Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status
+	@case '$?' in \
+	  *config.status*) \
+	    cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \
+	  *) \
+	    echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)'; \
+	    cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \
+	esac;
+
+$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+
+$(top_srcdir)/configure:  $(am__configure_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+$(ACLOCAL_M4):  $(am__aclocal_m4_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+uninstall-info-am:
+install-dictDATA: $(dict_DATA)
+	@$(NORMAL_INSTALL)
+	test -z "$(dictdir)" || $(mkdir_p) "$(DESTDIR)$(dictdir)"
+	@list='$(dict_DATA)'; for p in $$list; do \
+	  if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \
+	  f=$(am__strip_dir) \
+	  echo " $(dictDATA_INSTALL) '$$d$$p' '$(DESTDIR)$(dictdir)/$$f'"; \
+	  $(dictDATA_INSTALL) "$$d$$p" "$(DESTDIR)$(dictdir)/$$f"; \
+	done
+
+uninstall-dictDATA:
+	@$(NORMAL_UNINSTALL)
+	@list='$(dict_DATA)'; for p in $$list; do \
+	  f=$(am__strip_dir) \
+	  echo " rm -f '$(DESTDIR)$(dictdir)/$$f'"; \
+	  rm -f "$(DESTDIR)$(dictdir)/$$f"; \
+	done
+tags: TAGS
+TAGS:
+
+ctags: CTAGS
+CTAGS:
+
+
+distdir: $(DISTFILES)
+	@srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; \
+	topsrcdirstrip=`echo "$(top_srcdir)" | sed 's|.|.|g'`; \
+	list='$(DISTFILES)'; for file in $$list; do \
+	  case $$file in \
+	    $(srcdir)/*) file=`echo "$$file" | sed "s|^$$srcdirstrip/||"`;; \
+	    $(top_srcdir)/*) file=`echo "$$file" | sed "s|^$$topsrcdirstrip/|$(top_builddir)/|"`;; \
+	  esac; \
+	  if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \
+	  dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \
+	  if test "$$dir" != "$$file" && test "$$dir" != "."; then \
+	    dir="/$$dir"; \
+	    $(mkdir_p) "$(distdir)$$dir"; \
+	  else \
+	    dir=''; \
+	  fi; \
+	  if test -d $$d/$$file; then \
+	    if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \
+	      cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \
+	    fi; \
+	    cp -pR $$d/$$file $(distdir)$$dir || exit 1; \
+	  else \
+	    test -f $(distdir)/$$file \
+	    || cp -p $$d/$$file $(distdir)/$$file \
+	    || exit 1; \
+	  fi; \
+	done
+check-am: all-am
+check: check-am
+all-am: Makefile $(DATA)
+installdirs:
+	for dir in "$(DESTDIR)$(dictdir)"; do \
+	  test -z "$$dir" || $(mkdir_p) "$$dir"; \
+	done
+install: install-am
+install-exec: install-exec-am
+install-data: install-data-am
+uninstall: uninstall-am
+
+install-am: all-am
+	@$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am
+
+installcheck: installcheck-am
+install-strip:
+	$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
+	  install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
+	  `test -z '$(STRIP)' || \
+	    echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
+mostlyclean-generic:
+
+clean-generic:
+
+distclean-generic:
+	-test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES)
+
+maintainer-clean-generic:
+	@echo "This command is intended for maintainers to use"
+	@echo "it deletes files that may require special tools to rebuild."
+clean: clean-am
+
+clean-am: clean-generic mostlyclean-am
+
+distclean: distclean-am
+	-rm -f Makefile
+distclean-am: clean-am distclean-generic
+
+dvi: dvi-am
+
+dvi-am:
+
+html: html-am
+
+info: info-am
+
+info-am:
+
+install-data-am: install-dictDATA
+
+install-exec-am:
+
+install-info: install-info-am
+
+install-man:
+
+installcheck-am:
+
+maintainer-clean: maintainer-clean-am
+	-rm -f Makefile
+maintainer-clean-am: distclean-am maintainer-clean-generic
+
+mostlyclean: mostlyclean-am
+
+mostlyclean-am: mostlyclean-generic
+
+pdf: pdf-am
+
+pdf-am:
+
+ps: ps-am
+
+ps-am:
+
+uninstall-am: uninstall-dictDATA uninstall-info-am
+
+.PHONY: all all-am check check-am clean clean-generic distclean \
+	distclean-generic distdir dvi dvi-am html html-am info info-am \
+	install install-am install-data install-data-am \
+	install-dictDATA install-exec install-exec-am install-info \
+	install-info-am install-man install-strip installcheck \
+	installcheck-am installdirs maintainer-clean \
+	maintainer-clean-generic mostlyclean mostlyclean-generic pdf \
+	pdf-am ps ps-am uninstall uninstall-am uninstall-dictDATA \
+	uninstall-info-am
+
+# Tell versions [3.59,3.63) of GNU make to not export all variables.
+# Otherwise a system limit (for SysV at least) may be exceeded.
+.NOEXPORT:

corpora/en/wordnet/dict/Makefile.am

@@ -0,0 +1,2 @@
+dictdir = $(prefix)/dict
+dict_DATA = adj.exc adv.exc cntlist cntlist.rev data.adj data.adv data.noun data.verb frames.vrb index.adj index.adv index.noun index.sense index.verb log.grind.3.0 noun.exc sentidx.vrb sents.vrb verb.Framestext verb.exc lexnames

corpora/en/wordnet/dict/Makefile.in

@@ -0,0 +1,314 @@
+# Makefile.in generated by automake 1.9 from Makefile.am.
+# @configure_input@
+
+# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
+# 2003, 2004  Free Software Foundation, Inc.
+# This Makefile.in is free software; the Free Software Foundation
+# gives unlimited permission to copy and/or distribute it,
+# with or without modifications, as long as this notice is preserved.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
+# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+# PARTICULAR PURPOSE.
+
+@SET_MAKE@
+
+srcdir = @srcdir@
+top_srcdir = @top_srcdir@
+VPATH = @srcdir@
+pkgdatadir = $(datadir)/@PACKAGE@
+pkglibdir = $(libdir)/@PACKAGE@
+pkgincludedir = $(includedir)/@PACKAGE@
+top_builddir = ..
+am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd
+INSTALL = @INSTALL@
+install_sh_DATA = $(install_sh) -c -m 644
+install_sh_PROGRAM = $(install_sh) -c
+install_sh_SCRIPT = $(install_sh) -c
+INSTALL_HEADER = $(INSTALL_DATA)
+transform = $(program_transform_name)
+NORMAL_INSTALL = :
+PRE_INSTALL = :
+POST_INSTALL = :
+NORMAL_UNINSTALL = :
+PRE_UNINSTALL = :
+POST_UNINSTALL = :
+subdir = dict
+DIST_COMMON = $(srcdir)/Makefile.am $(srcdir)/Makefile.in
+ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
+am__aclocal_m4_deps = $(top_srcdir)/acinclude.m4 \
+	$(top_srcdir)/configure.ac
+am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
+	$(ACLOCAL_M4)
+mkinstalldirs = $(install_sh) -d
+CONFIG_HEADER = $(top_builddir)/config.h
+CONFIG_CLEAN_FILES =
+SOURCES =
+DIST_SOURCES =
+am__vpath_adj_setup = srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`;
+am__vpath_adj = case $$p in \
+    $(srcdir)/*) f=`echo "$$p" | sed "s|^$$srcdirstrip/||"`;; \
+    *) f=$$p;; \
+  esac;
+am__strip_dir = `echo $$p | sed -e 's|^.*/||'`;
+am__installdirs = "$(DESTDIR)$(dictdir)"
+dictDATA_INSTALL = $(INSTALL_DATA)
+DATA = $(dict_DATA)
+DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
+ACLOCAL = @ACLOCAL@
+AMDEP_FALSE = @AMDEP_FALSE@
+AMDEP_TRUE = @AMDEP_TRUE@
+AMTAR = @AMTAR@
+AUTOCONF = @AUTOCONF@
+AUTOHEADER = @AUTOHEADER@
+AUTOMAKE = @AUTOMAKE@
+AWK = @AWK@
+CC = @CC@
+CCDEPMODE = @CCDEPMODE@
+CFLAGS = @CFLAGS@
+CPP = @CPP@
+CPPFLAGS = @CPPFLAGS@
+CYGPATH_W = @CYGPATH_W@
+DEFS = @DEFS@
+DEPDIR = @DEPDIR@
+ECHO_C = @ECHO_C@
+ECHO_N = @ECHO_N@
+ECHO_T = @ECHO_T@
+EGREP = @EGREP@
+EXEEXT = @EXEEXT@
+INSTALL_DATA = @INSTALL_DATA@
+INSTALL_PROGRAM = @INSTALL_PROGRAM@
+INSTALL_SCRIPT = @INSTALL_SCRIPT@
+INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@
+LDFLAGS = @LDFLAGS@
+LIBOBJS = @LIBOBJS@
+LIBS = @LIBS@
+LTLIBOBJS = @LTLIBOBJS@
+MAKEINFO = @MAKEINFO@
+OBJEXT = @OBJEXT@
+PACKAGE = @PACKAGE@
+PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@
+PACKAGE_NAME = @PACKAGE_NAME@
+PACKAGE_STRING = @PACKAGE_STRING@
+PACKAGE_TARNAME = @PACKAGE_TARNAME@
+PACKAGE_VERSION = @PACKAGE_VERSION@
+PATH_SEPARATOR = @PATH_SEPARATOR@
+RANLIB = @RANLIB@
+SET_MAKE = @SET_MAKE@
+SHELL = @SHELL@
+STRIP = @STRIP@
+TCL_INCLUDE_SPEC = @TCL_INCLUDE_SPEC@
+TCL_LIB_SPEC = @TCL_LIB_SPEC@
+TK_LIBS = @TK_LIBS@
+TK_LIB_SPEC = @TK_LIB_SPEC@
+TK_PREFIX = @TK_PREFIX@
+TK_XINCLUDES = @TK_XINCLUDES@
+VERSION = @VERSION@
+ac_ct_CC = @ac_ct_CC@
+ac_ct_RANLIB = @ac_ct_RANLIB@
+ac_ct_STRIP = @ac_ct_STRIP@
+ac_prefix = @ac_prefix@
+am__fastdepCC_FALSE = @am__fastdepCC_FALSE@
+am__fastdepCC_TRUE = @am__fastdepCC_TRUE@
+am__include = @am__include@
+am__leading_dot = @am__leading_dot@
+am__quote = @am__quote@
+am__tar = @am__tar@
+am__untar = @am__untar@
+bindir = @bindir@
+build_alias = @build_alias@
+datadir = @datadir@
+exec_prefix = @exec_prefix@
+host_alias = @host_alias@
+includedir = @includedir@
+infodir = @infodir@
+install_sh = @install_sh@
+libdir = @libdir@
+libexecdir = @libexecdir@
+localstatedir = @localstatedir@
+mandir = @mandir@
+mkdir_p = @mkdir_p@
+oldincludedir = @oldincludedir@
+prefix = @prefix@
+program_transform_name = @program_transform_name@
+sbindir = @sbindir@
+sharedstatedir = @sharedstatedir@
+sysconfdir = @sysconfdir@
+target_alias = @target_alias@
+dictdir = $(prefix)/dict
+dict_DATA = adj.exc adv.exc cntlist cntlist.rev data.adj data.adv data.noun data.verb frames.vrb index.adj index.adv index.noun index.sense index.verb log.grind.3.0 noun.exc sentidx.vrb sents.vrb verb.Framestext verb.exc lexnames
+all: all-am
+
+.SUFFIXES:
+$(srcdir)/Makefile.in:  $(srcdir)/Makefile.am  $(am__configure_deps)
+	@for dep in $?; do \
+	  case '$(am__configure_deps)' in \
+	    *$$dep*) \
+	      cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh \
+		&& exit 0; \
+	      exit 1;; \
+	  esac; \
+	done; \
+	echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu  dict/Makefile'; \
+	cd $(top_srcdir) && \
+	  $(AUTOMAKE) --gnu  dict/Makefile
+.PRECIOUS: Makefile
+Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status
+	@case '$?' in \
+	  *config.status*) \
+	    cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \
+	  *) \
+	    echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)'; \
+	    cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \
+	esac;
+
+$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+
+$(top_srcdir)/configure:  $(am__configure_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+$(ACLOCAL_M4):  $(am__aclocal_m4_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+uninstall-info-am:
+install-dictDATA: $(dict_DATA)
+	@$(NORMAL_INSTALL)
+	test -z "$(dictdir)" || $(mkdir_p) "$(DESTDIR)$(dictdir)"
+	@list='$(dict_DATA)'; for p in $$list; do \
+	  if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \
+	  f=$(am__strip_dir) \
+	  echo " $(dictDATA_INSTALL) '$$d$$p' '$(DESTDIR)$(dictdir)/$$f'"; \
+	  $(dictDATA_INSTALL) "$$d$$p" "$(DESTDIR)$(dictdir)/$$f"; \
+	done
+
+uninstall-dictDATA:
+	@$(NORMAL_UNINSTALL)
+	@list='$(dict_DATA)'; for p in $$list; do \
+	  f=$(am__strip_dir) \
+	  echo " rm -f '$(DESTDIR)$(dictdir)/$$f'"; \
+	  rm -f "$(DESTDIR)$(dictdir)/$$f"; \
+	done
+tags: TAGS
+TAGS:
+
+ctags: CTAGS
+CTAGS:
+
+
+distdir: $(DISTFILES)
+	@srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; \
+	topsrcdirstrip=`echo "$(top_srcdir)" | sed 's|.|.|g'`; \
+	list='$(DISTFILES)'; for file in $$list; do \
+	  case $$file in \
+	    $(srcdir)/*) file=`echo "$$file" | sed "s|^$$srcdirstrip/||"`;; \
+	    $(top_srcdir)/*) file=`echo "$$file" | sed "s|^$$topsrcdirstrip/|$(top_builddir)/|"`;; \
+	  esac; \
+	  if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \
+	  dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \
+	  if test "$$dir" != "$$file" && test "$$dir" != "."; then \
+	    dir="/$$dir"; \
+	    $(mkdir_p) "$(distdir)$$dir"; \
+	  else \
+	    dir=''; \
+	  fi; \
+	  if test -d $$d/$$file; then \
+	    if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \
+	      cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \
+	    fi; \
+	    cp -pR $$d/$$file $(distdir)$$dir || exit 1; \
+	  else \
+	    test -f $(distdir)/$$file \
+	    || cp -p $$d/$$file $(distdir)/$$file \
+	    || exit 1; \
+	  fi; \
+	done
+check-am: all-am
+check: check-am
+all-am: Makefile $(DATA)
+installdirs:
+	for dir in "$(DESTDIR)$(dictdir)"; do \
+	  test -z "$$dir" || $(mkdir_p) "$$dir"; \
+	done
+install: install-am
+install-exec: install-exec-am
+install-data: install-data-am
+uninstall: uninstall-am
+
+install-am: all-am
+	@$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am
+
+installcheck: installcheck-am
+install-strip:
+	$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
+	  install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
+	  `test -z '$(STRIP)' || \
+	    echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
+mostlyclean-generic:
+
+clean-generic:
+
+distclean-generic:
+	-test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES)
+
+maintainer-clean-generic:
+	@echo "This command is intended for maintainers to use"
+	@echo "it deletes files that may require special tools to rebuild."
+clean: clean-am
+
+clean-am: clean-generic mostlyclean-am
+
+distclean: distclean-am
+	-rm -f Makefile
+distclean-am: clean-am distclean-generic
+
+dvi: dvi-am
+
+dvi-am:
+
+html: html-am
+
+info: info-am
+
+info-am:
+
+install-data-am: install-dictDATA
+
+install-exec-am:
+
+install-info: install-info-am
+
+install-man:
+
+installcheck-am:
+
+maintainer-clean: maintainer-clean-am
+	-rm -f Makefile
+maintainer-clean-am: distclean-am maintainer-clean-generic
+
+mostlyclean: mostlyclean-am
+
+mostlyclean-am: mostlyclean-generic
+
+pdf: pdf-am
+
+pdf-am:
+
+ps: ps-am
+
+ps-am:
+
+uninstall-am: uninstall-dictDATA uninstall-info-am
+
+.PHONY: all all-am check check-am clean clean-generic distclean \
+	distclean-generic distdir dvi dvi-am html html-am info info-am \
+	install install-am install-data install-data-am \
+	install-dictDATA install-exec install-exec-am install-info \
+	install-info-am install-man install-strip installcheck \
+	installcheck-am installdirs maintainer-clean \
+	maintainer-clean-generic mostlyclean mostlyclean-generic pdf \
+	pdf-am ps ps-am uninstall uninstall-am uninstall-dictDATA \
+	uninstall-info-am
+
+# Tell versions [3.59,3.63) of GNU make to not export all variables.
+# Otherwise a system limit (for SysV at least) may be exceeded.
+.NOEXPORT:

corpora/en/wordnet/dict/adv.exc

@@ -0,0 +1,7 @@
+best well
+better well
+deeper deeply
+farther far
+further far
+harder hard
+hardest hard

corpora/en/wordnet/dict/frames.vrb

@@ -0,0 +1,35 @@
+1  Something ----s
+2  Somebody ----s
+3  It is ----ing
+4  Something is ----ing PP
+5  Something ----s something Adjective/Noun
+6  Something ----s Adjective/Noun
+7  Somebody ----s Adjective
+8  Somebody ----s something
+9  Somebody ----s somebody
+10 Something ----s somebody
+11 Something ----s something
+12 Something ----s to somebody
+13 Somebody ----s on something
+14 Somebody ----s somebody something
+15 Somebody ----s something to somebody
+16 Somebody ----s something from somebody
+17 Somebody ----s somebody with something
+18 Somebody ----s somebody of something
+19 Somebody ----s something on somebody
+20 Somebody ----s somebody PP
+21 Somebody ----s something PP
+22 Somebody ----s PP
+23 Somebody's (body part) ----s
+24 Somebody ----s somebody to INFINITIVE
+25 Somebody ----s somebody INFINITIVE
+26 Somebody ----s that CLAUSE
+27 Somebody ----s to somebody
+28 Somebody ----s to INFINITIVE
+29 Somebody ----s whether INFINITIVE
+30 Somebody ----s somebody into V-ing something
+31 Somebody ----s something with something
+32 Somebody ----s INFINITIVE
+33 Somebody ----s VERB-ing
+34 It ----s that CLAUSE
+35 Something ----s INFINITIVE

corpora/en/wordnet/dict/lexnames

@@ -0,0 +1,45 @@
+00	adj.all	3
+01	adj.pert	3 
+02	adv.all	4
+03	noun.Tops	1  
+04	noun.act	1
+05	noun.animal	1
+06	noun.artifact	1
+07	noun.attribute	1
+08	noun.body	1
+09	noun.cognition	1
+10	noun.communication	1
+11	noun.event	1
+12	noun.feeling	1
+13	noun.food	1
+14	noun.group	1
+15	noun.location	1
+16	noun.motive	1
+17	noun.object	1
+18	noun.person	1
+19	noun.phenomenon	1
+20	noun.plant	1
+21	noun.possession	1
+22	noun.process	1
+23	noun.quantity	1
+24	noun.relation	1
+25	noun.shape	1
+26	noun.state	1
+27	noun.substance	1
+28	noun.time	1
+29	verb.body	2
+30	verb.change	2
+31	verb.cognition	2
+32	verb.communication	2
+33	verb.competition	2
+34	verb.consumption	2
+35	verb.contact	2
+36	verb.creation	2
+37	verb.emotion	2
+38	verb.motion	2
+39	verb.perception	2
+40	verb.possession	2
+41	verb.social	2
+42	verb.stative	2
+43	verb.weather	2
+44	adj.ppl	3

corpora/en/wordnet/dict/log.grind.3.0

@@ -0,0 +1,89 @@
+Processing adj.all...
+Processing adj.pert...
+Processing adv.all...
+Processing noun.Tops...
+noun.Tops, line 7: warning: No hypernyms in synset
+Processing noun.act...
+Processing noun.animal...
+Processing noun.artifact...
+Processing noun.attribute...
+Processing noun.body...
+Processing noun.cognition...
+Processing noun.communication...
+Processing noun.event...
+Processing noun.feeling...
+Processing noun.food...
+Processing noun.group...
+Processing noun.location...
+Processing noun.motive...
+Processing noun.object...
+Processing noun.person...
+Processing noun.phenomenon...
+Processing noun.plant...
+Processing noun.possession...
+Processing noun.process...
+Processing noun.quantity...
+Processing noun.relation...
+Processing noun.shape...
+Processing noun.state...
+Processing noun.substance...
+Processing noun.time...
+Processing verb.body...
+Processing verb.change...
+Processing verb.cognition...
+Processing verb.communication...
+Processing verb.competition...
+Processing verb.consumption...
+Processing verb.contact...
+Processing verb.creation...
+Processing verb.emotion...
+Processing verb.motion...
+Processing verb.perception...
+Processing verb.possession...
+Processing verb.social...
+Processing verb.stative...
+Processing verb.weather...
+Processing adj.ppl...
+
+*** Statistics for ground files:
+
+82115 noun synsets
+13767 verb synsets
+3812 adj synsets
+3621 adv synsets
+3651 pertainym synsets
+10693 adjective satellite synsets
+117659 synsets in total (including satellite and pertainym synsets)
+82115 noun synsets have definitional glosses
+13767 verb synsets have definitional glosses
+3812 adj synsets have definitional glosses
+3621 adv synsets have definitional glosses
+3651 pertainym synsets have definitional glosses
+10693 adjective satellite synsets have definitional glosses
+117659 definitional glosses in total (including adjective satellite synsets)
+225000 pointers in total
+206978 synonyms in synsets
+147306 unique word phrases
+83118 word phrases of length 1
+54533 word phrases of length 2
+7766 word phrases of length 3
+1454 word phrases of length 4
+298 word phrases of length 5
+80 word phrases of length 6
+28 word phrases of length 7
+20 word phrases of length 8
+9 word phrases of length 9
+
+Resolving pointers...
+Done resolving pointers...
+Getting sense counts...
+Done with sense counts...
+Figuring out byte offsets...
+Dumping data files...
+Done dumping data files...
+Cannot open file: cntlist
+Cannot order senses
+Dumping index files...
+Done dumping index files...
+Dumping sense index...
+Done dumping sense index...

corpora/en/wordnet/dict/sents.vrb

@@ -0,0 +1,170 @@
+1 The children %s to the playground
+10 The cars %s down the avenue
+100 These glasses %s easily
+101 These fabrics %s easily
+102 They %s their earnings this year
+103 Their earnings %s this year
+104 The water %ss 
+105 They %s the water 
+106 The animals %s
+107 They %s a long time
+108 The car %ss the tree 
+109 John will %s angry
+11 They %s the car down the avenue
+110 They %s in the city
+111 They won't %s the story 
+112 They %s that there was a traffic accident 
+113 They %s whether there was a traffic accident
+114 They %s her vice president
+115 Did he %s his major works over a short period of time?
+116 The chefs %s the vegetables
+117 They %s the cape 
+118 The food does %s good 
+119 The music does %s good 
+12 They %s the glass tubes
+120 The cool air does %s good
+121 This food does %s well 
+122 It was %sing all day long 
+123 They %s him to write the letter
+124 They %s him into writing the letter
+125 They %s him from writing the letter
+126 The bad news will %s him
+127 The good news will %s her
+128 The chef wants to %s the eggs 
+129 Sam wants to %s with Sue 
+13 The glass tubes %s
+130 The fighter managed to %s his opponent
+131 These cars won't %s 
+132 The branches %s from the trees
+133 The stock market is going to %s 
+134 The moon will soon %s 
+135 The business is going to %s 
+136 The airplane is sure to %s 
+137 They %s to move 
+138 They %s moving 
+139 Sam and Sue %s the movie 
+14 Sam and Sue %s
+140 They want to %s the prisoners 
+141 They want to %s the doors
+142 The doors %s 
+143 Did he %s his foot? 
+144 Did his feet %s?
+145 They will %s the duet
+146 They %s their hair 
+147 They %s the trees
+148 They %s him of all his money
+149 Lights %s on the horizon
+15 Sam cannot %s Sue 
+150 The horizon is %sing with lights
+151 The crowds %s in the streets
+152 The streets %s with crowds
+153 Cars %s in the streets 
+154 The streets %s with cars 
+155 You can hear animals %s in the meadows
+156 The meadows %s with animals 
+157 The birds %s in the woods 
+158 The woods %s with many kinds of birds 
+159 The performance is likely to %s Sue
+16 The ropes %s
+160 Sam and Sue %s over the results of the experiment
+161 In the summer they like to go out and %s
+162 The children %s in the rocking chair
+163 There %s some children in the rocking chair
+164 Some big birds %s in the tree
+165 There %s some big birds in the tree
+166 The men %s the area for animals 
+167 The men %s for animals in the area
+168 The customs agents %s the bags for drugs 
+169 They %s him as chairman 
+17 The strong winds %s the rope
+170 They %s him "Bobby"
+18 They %s the sheets
+19 The sheets didn't %s
+2 The banks %s the check
+20 The horses %s across the field
+21 They %s the bags on the table
+22 The men %s the horses across the field
+23 Our properties %s at this point
+24 His fields %s mine at this point
+25 They %s the hill
+26 They %s up the hill
+27 They %s the river
+28 They %s down the river 
+29 They %s the countryside
+3 The checks %s 
+30 They %s in the countryside
+31 These men %s across the river
+32 These men %s the river
+33 They %s the food to the people
+34 They %s the people the food
+35 They %s more bread
+36 They %s the object in the water
+37 The men %s the bookshelves
+38 They %s the money in the closet
+39 The lights %s from the ceiling
+4 The children %s the ball
+40 They %s the lights from the ceiling
+41 They %s their rifles on the cabinet
+42 The chairs %s in the corner
+43 The men %s the chairs
+44 The women %s water into the bowl
+45 Water and oil %s into the bowl
+46 They %s the wire around the stick
+47 The wires %s around the stick
+48 They %s the bread with melted butter
+49 They %s the cart with boxes 
+5 The balls %s 
+50 They %s the books into the box
+51 They %s sugar over the cake
+52 They %s the cake with sugar
+53 They %s the fruit with a chemical
+54 They %s a chemical into the fruit
+55 They %s the field with rye
+56 They %s rye in the field
+57 They %s notices on the doors
+58 They %s the doors with notices
+59 They %s money on their grandchild
+6 The girls %s the wooden sticks
+60 They %s their grandchild with money
+61 They %s coins on the image 
+62 They %s the image with coins 
+63 They %s butter on the bread
+64 They %s the lake with fish
+65 The children %s the paper with grease 
+66 The children %s grease onto the paper
+67 They %s papers over the floor
+68 They %s the floor with papers
+69 They %s the money 
+7 The wooden sticks %s 
+70 They %s the newspapers
+71 They %s the goods
+72 The men %s the boat 
+73 They %s the animals
+74 The books %s the box 
+75 They %s the halls with holly
+76 Holly flowers %s the halls
+77 The wind storms %s the area with dust and dirt
+78 Dust and dirt %s the area
+79 The swollen rivers %s the area with water
+8 The coins %s 
+80 The waters %s the area
+81 They %s the cloth with water and alcohol
+82 Water and alcohol %s the cloth
+83 They %s the snow from the path
+84 They %s the path of the snow
+85 They %s the water from the sink
+86 They %s the sink of water
+87 They %s the parcel to their parents
+88 They %s them the parcel
+89 They %s cars to the tourists
+9 They %s the coin 
+90 They %s the tourists their cars
+91 They %s the money to them 
+92 They %s them the money
+93 They %s them the information
+94 They %s the information to them
+95 The parents %s a French poem to the children
+96 The parents %s the children a French poem 
+97 They %s 
+98 They %s themselves
+99 These balls %s easily

corpora/en/wordnet/dict/verb.Framestext

@@ -0,0 +1,35 @@
+1  Something ----s
+2  Somebody ----s
+3  It is ----ing
+4  Something is ----ing PP
+5  Something ----s something Adjective/Noun
+6  Something ----s Adjective/Noun
+7  Somebody ----s Adjective
+8  Somebody ----s something
+9  Somebody ----s somebody
+10 Something ----s somebody
+11 Something ----s something
+12 Something ----s to somebody
+13 Somebody ----s on something
+14 Somebody ----s somebody something
+15 Somebody ----s something to somebody
+16 Somebody ----s something from somebody
+17 Somebody ----s somebody with something
+18 Somebody ----s somebody of something
+19 Somebody ----s something on somebody
+20 Somebody ----s somebody PP
+21 Somebody ----s something PP
+22 Somebody ----s PP
+23 Somebody's (body part) ----s
+24 Somebody ----s somebody to INFINITIVE
+25 Somebody ----s somebody INFINITIVE
+26 Somebody ----s that CLAUSE
+27 Somebody ----s to somebody
+28 Somebody ----s to INFINITIVE
+29 Somebody ----s whether INFINITIVE
+30 Somebody ----s somebody into V-ing something
+31 Somebody ----s something with something
+32 Somebody ----s INFINITIVE
+33 Somebody ----s VERB-ing
+34 It ----s that CLAUSE
+35 Something ----s INFINITIVE

corpora/en/wordnet/doc/Makefile

@@ -0,0 +1,426 @@
+# Makefile.in generated by automake 1.9 from Makefile.am.
+# doc/Makefile.  Generated from Makefile.in by configure.
+
+# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
+# 2003, 2004  Free Software Foundation, Inc.
+# This Makefile.in is free software; the Free Software Foundation
+# gives unlimited permission to copy and/or distribute it,
+# with or without modifications, as long as this notice is preserved.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
+# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+# PARTICULAR PURPOSE.
+
+
+srcdir = .
+top_srcdir = ..
+
+pkgdatadir = $(datadir)/WordNet
+pkglibdir = $(libdir)/WordNet
+pkgincludedir = $(includedir)/WordNet
+top_builddir = ..
+am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd
+INSTALL = /usr/csl/bin/install -c
+install_sh_DATA = $(install_sh) -c -m 644
+install_sh_PROGRAM = $(install_sh) -c
+install_sh_SCRIPT = $(install_sh) -c
+INSTALL_HEADER = $(INSTALL_DATA)
+transform = $(program_transform_name)
+NORMAL_INSTALL = :
+PRE_INSTALL = :
+POST_INSTALL = :
+NORMAL_UNINSTALL = :
+PRE_UNINSTALL = :
+POST_UNINSTALL = :
+subdir = doc
+DIST_COMMON = $(srcdir)/Makefile.am $(srcdir)/Makefile.in
+ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
+am__aclocal_m4_deps = $(top_srcdir)/acinclude.m4 \
+	$(top_srcdir)/configure.ac
+am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
+	$(ACLOCAL_M4)
+mkinstalldirs = $(install_sh) -d
+CONFIG_HEADER = $(top_builddir)/config.h
+CONFIG_CLEAN_FILES =
+SOURCES =
+DIST_SOURCES =
+RECURSIVE_TARGETS = all-recursive check-recursive dvi-recursive \
+	html-recursive info-recursive install-data-recursive \
+	install-exec-recursive install-info-recursive \
+	install-recursive installcheck-recursive installdirs-recursive \
+	pdf-recursive ps-recursive uninstall-info-recursive \
+	uninstall-recursive
+ETAGS = etags
+CTAGS = ctags
+DIST_SUBDIRS = $(SUBDIRS)
+DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
+ACLOCAL = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run aclocal-1.9
+AMDEP_FALSE = #
+AMDEP_TRUE = 
+AMTAR = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run tar
+AUTOCONF = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run autoconf
+AUTOHEADER = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run autoheader
+AUTOMAKE = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run automake-1.9
+AWK = nawk
+CC = gcc
+CCDEPMODE = depmode=gcc3
+CFLAGS = -g -O2
+CPP = gcc -E
+CPPFLAGS = 
+CYGPATH_W = echo
+DEFS = -DHAVE_CONFIG_H
+DEPDIR = .deps
+ECHO_C = 
+ECHO_N = -n
+ECHO_T = 
+EGREP = egrep
+EXEEXT = 
+INSTALL_DATA = ${INSTALL} -m 644
+INSTALL_PROGRAM = ${INSTALL}
+INSTALL_SCRIPT = ${INSTALL}
+INSTALL_STRIP_PROGRAM = ${SHELL} $(install_sh) -c -s
+LDFLAGS = 
+LIBOBJS = 
+LIBS = 
+LTLIBOBJS = 
+MAKEINFO = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run makeinfo
+OBJEXT = o
+PACKAGE = WordNet
+PACKAGE_BUGREPORT = wordnet@princeton.edu
+PACKAGE_NAME = WordNet
+PACKAGE_STRING = WordNet 3.0
+PACKAGE_TARNAME = wordnet
+PACKAGE_VERSION = 3.0
+PATH_SEPARATOR = :
+RANLIB = ranlib
+SET_MAKE = 
+SHELL = /bin/bash
+STRIP = 
+TCL_INCLUDE_SPEC = -I/usr/csl/include
+TCL_LIB_SPEC = -L/usr/csl/lib -ltcl8.4
+TK_LIBS = -L/usr/openwin/lib -lX11 -ldl  -lpthread -lsocket -lnsl -lm
+TK_LIB_SPEC = -L/usr/csl/lib -ltk8.4
+TK_PREFIX = /usr/csl
+TK_XINCLUDES = -I/usr/openwin/include
+VERSION = 3.0
+ac_ct_CC = gcc
+ac_ct_RANLIB = ranlib
+ac_ct_STRIP = 
+ac_prefix = /usr/local/WordNet-3.0
+am__fastdepCC_FALSE = #
+am__fastdepCC_TRUE = 
+am__include = include
+am__leading_dot = .
+am__quote = 
+am__tar = ${AMTAR} chof - "$$tardir"
+am__untar = ${AMTAR} xf -
+bindir = ${exec_prefix}/bin
+build_alias = 
+datadir = ${prefix}/share
+exec_prefix = ${prefix}
+host_alias = 
+includedir = ${prefix}/include
+infodir = ${prefix}/info
+install_sh = /people/wn/src/Release/3.0/Unix/install-sh
+libdir = ${exec_prefix}/lib
+libexecdir = ${exec_prefix}/libexec
+localstatedir = ${prefix}/var
+mandir = ${prefix}/man
+mkdir_p = $(install_sh) -d
+oldincludedir = /usr/include
+prefix = /usr/local/WordNet-3.0
+program_transform_name = s,x,x,
+sbindir = ${exec_prefix}/sbin
+sharedstatedir = ${prefix}/com
+sysconfdir = ${prefix}/etc
+target_alias = 
+SUBDIRS = html man pdf ps
+all: all-recursive
+
+.SUFFIXES:
+$(srcdir)/Makefile.in:  $(srcdir)/Makefile.am  $(am__configure_deps)
+	@for dep in $?; do \
+	  case '$(am__configure_deps)' in \
+	    *$$dep*) \
+	      cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh \
+		&& exit 0; \
+	      exit 1;; \
+	  esac; \
+	done; \
+	echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu  doc/Makefile'; \
+	cd $(top_srcdir) && \
+	  $(AUTOMAKE) --gnu  doc/Makefile
+.PRECIOUS: Makefile
+Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status
+	@case '$?' in \
+	  *config.status*) \
+	    cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \
+	  *) \
+	    echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)'; \
+	    cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \
+	esac;
+
+$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+
+$(top_srcdir)/configure:  $(am__configure_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+$(ACLOCAL_M4):  $(am__aclocal_m4_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+uninstall-info-am:
+
+# This directory's subdirectories are mostly independent; you can cd
+# into them and run `make' without going through this Makefile.
+# To change the values of `make' variables: instead of editing Makefiles,
+# (1) if the variable is set in `config.status', edit `config.status'
+#     (which will cause the Makefiles to be regenerated when you run `make');
+# (2) otherwise, pass the desired values on the `make' command line.
+$(RECURSIVE_TARGETS):
+	@set fnord $$MAKEFLAGS; amf=$$2; \
+	dot_seen=no; \
+	target=`echo $@ | sed s/-recursive//`; \
+	list='$(SUBDIRS)'; for subdir in $$list; do \
+	  echo "Making $$target in $$subdir"; \
+	  if test "$$subdir" = "."; then \
+	    dot_seen=yes; \
+	    local_target="$$target-am"; \
+	  else \
+	    local_target="$$target"; \
+	  fi; \
+	  (cd $$subdir && $(MAKE) $(AM_MAKEFLAGS) $$local_target) \
+	   || case "$$amf" in *=*) exit 1;; *k*) fail=yes;; *) exit 1;; esac; \
+	done; \
+	if test "$$dot_seen" = "no"; then \
+	  $(MAKE) $(AM_MAKEFLAGS) "$$target-am" || exit 1; \
+	fi; test -z "$$fail"
+
+mostlyclean-recursive clean-recursive distclean-recursive \
+maintainer-clean-recursive:
+	@set fnord $$MAKEFLAGS; amf=$$2; \
+	dot_seen=no; \
+	case "$@" in \
+	  distclean-* | maintainer-clean-*) list='$(DIST_SUBDIRS)' ;; \
+	  *) list='$(SUBDIRS)' ;; \
+	esac; \
+	rev=''; for subdir in $$list; do \
+	  if test "$$subdir" = "."; then :; else \
+	    rev="$$subdir $$rev"; \
+	  fi; \
+	done; \
+	rev="$$rev ."; \
+	target=`echo $@ | sed s/-recursive//`; \
+	for subdir in $$rev; do \
+	  echo "Making $$target in $$subdir"; \
+	  if test "$$subdir" = "."; then \
+	    local_target="$$target-am"; \
+	  else \
+	    local_target="$$target"; \
+	  fi; \
+	  (cd $$subdir && $(MAKE) $(AM_MAKEFLAGS) $$local_target) \
+	   || case "$$amf" in *=*) exit 1;; *k*) fail=yes;; *) exit 1;; esac; \
+	done && test -z "$$fail"
+tags-recursive:
+	list='$(SUBDIRS)'; for subdir in $$list; do \
+	  test "$$subdir" = . || (cd $$subdir && $(MAKE) $(AM_MAKEFLAGS) tags); \
+	done
+ctags-recursive:
+	list='$(SUBDIRS)'; for subdir in $$list; do \
+	  test "$$subdir" = . || (cd $$subdir && $(MAKE) $(AM_MAKEFLAGS) ctags); \
+	done
+
+ID: $(HEADERS) $(SOURCES) $(LISP) $(TAGS_FILES)
+	list='$(SOURCES) $(HEADERS) $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	mkid -fID $$unique
+tags: TAGS
+
+TAGS: tags-recursive $(HEADERS) $(SOURCES)  $(TAGS_DEPENDENCIES) \
+		$(TAGS_FILES) $(LISP)
+	tags=; \
+	here=`pwd`; \
+	if ($(ETAGS) --etags-include --version) >/dev/null 2>&1; then \
+	  include_option=--etags-include; \
+	  empty_fix=.; \
+	else \
+	  include_option=--include; \
+	  empty_fix=; \
+	fi; \
+	list='$(SUBDIRS)'; for subdir in $$list; do \
+	  if test "$$subdir" = .; then :; else \
+	    test ! -f $$subdir/TAGS || \
+	      tags="$$tags $$include_option=$$here/$$subdir/TAGS"; \
+	  fi; \
+	done; \
+	list='$(SOURCES) $(HEADERS)  $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	if test -z "$(ETAGS_ARGS)$$tags$$unique"; then :; else \
+	  test -n "$$unique" || unique=$$empty_fix; \
+	  $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \
+	    $$tags $$unique; \
+	fi
+ctags: CTAGS
+CTAGS: ctags-recursive $(HEADERS) $(SOURCES)  $(TAGS_DEPENDENCIES) \
+		$(TAGS_FILES) $(LISP)
+	tags=; \
+	here=`pwd`; \
+	list='$(SOURCES) $(HEADERS)  $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	test -z "$(CTAGS_ARGS)$$tags$$unique" \
+	  || $(CTAGS) $(CTAGSFLAGS) $(AM_CTAGSFLAGS) $(CTAGS_ARGS) \
+	     $$tags $$unique
+
+GTAGS:
+	here=`$(am__cd) $(top_builddir) && pwd` \
+	  && cd $(top_srcdir) \
+	  && gtags -i $(GTAGS_ARGS) $$here
+
+distclean-tags:
+	-rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH tags
+
+distdir: $(DISTFILES)
+	@srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; \
+	topsrcdirstrip=`echo "$(top_srcdir)" | sed 's|.|.|g'`; \
+	list='$(DISTFILES)'; for file in $$list; do \
+	  case $$file in \
+	    $(srcdir)/*) file=`echo "$$file" | sed "s|^$$srcdirstrip/||"`;; \
+	    $(top_srcdir)/*) file=`echo "$$file" | sed "s|^$$topsrcdirstrip/|$(top_builddir)/|"`;; \
+	  esac; \
+	  if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \
+	  dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \
+	  if test "$$dir" != "$$file" && test "$$dir" != "."; then \
+	    dir="/$$dir"; \
+	    $(mkdir_p) "$(distdir)$$dir"; \
+	  else \
+	    dir=''; \
+	  fi; \
+	  if test -d $$d/$$file; then \
+	    if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \
+	      cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \
+	    fi; \
+	    cp -pR $$d/$$file $(distdir)$$dir || exit 1; \
+	  else \
+	    test -f $(distdir)/$$file \
+	    || cp -p $$d/$$file $(distdir)/$$file \
+	    || exit 1; \
+	  fi; \
+	done
+	list='$(DIST_SUBDIRS)'; for subdir in $$list; do \
+	  if test "$$subdir" = .; then :; else \
+	    test -d "$(distdir)/$$subdir" \
+	    || $(mkdir_p) "$(distdir)/$$subdir" \
+	    || exit 1; \
+	    distdir=`$(am__cd) $(distdir) && pwd`; \
+	    top_distdir=`$(am__cd) $(top_distdir) && pwd`; \
+	    (cd $$subdir && \
+	      $(MAKE) $(AM_MAKEFLAGS) \
+	        top_distdir="$$top_distdir" \
+	        distdir="$$distdir/$$subdir" \
+	        distdir) \
+	      || exit 1; \
+	  fi; \
+	done
+check-am: all-am
+check: check-recursive
+all-am: Makefile
+installdirs: installdirs-recursive
+installdirs-am:
+install: install-recursive
+install-exec: install-exec-recursive
+install-data: install-data-recursive
+uninstall: uninstall-recursive
+
+install-am: all-am
+	@$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am
+
+installcheck: installcheck-recursive
+install-strip:
+	$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
+	  install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
+	  `test -z '$(STRIP)' || \
+	    echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
+mostlyclean-generic:
+
+clean-generic:
+
+distclean-generic:
+	-test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES)
+
+maintainer-clean-generic:
+	@echo "This command is intended for maintainers to use"
+	@echo "it deletes files that may require special tools to rebuild."
+clean: clean-recursive
+
+clean-am: clean-generic mostlyclean-am
+
+distclean: distclean-recursive
+	-rm -f Makefile
+distclean-am: clean-am distclean-generic distclean-tags
+
+dvi: dvi-recursive
+
+dvi-am:
+
+html: html-recursive
+
+info: info-recursive
+
+info-am:
+
+install-data-am:
+
+install-exec-am:
+
+install-info: install-info-recursive
+
+install-man:
+
+installcheck-am:
+
+maintainer-clean: maintainer-clean-recursive
+	-rm -f Makefile
+maintainer-clean-am: distclean-am maintainer-clean-generic
+
+mostlyclean: mostlyclean-recursive
+
+mostlyclean-am: mostlyclean-generic
+
+pdf: pdf-recursive
+
+pdf-am:
+
+ps: ps-recursive
+
+ps-am:
+
+uninstall-am: uninstall-info-am
+
+uninstall-info: uninstall-info-recursive
+
+.PHONY: $(RECURSIVE_TARGETS) CTAGS GTAGS all all-am check check-am \
+	clean clean-generic clean-recursive ctags ctags-recursive \
+	distclean distclean-generic distclean-recursive distclean-tags \
+	distdir dvi dvi-am html html-am info info-am install \
+	install-am install-data install-data-am install-exec \
+	install-exec-am install-info install-info-am install-man \
+	install-strip installcheck installcheck-am installdirs \
+	installdirs-am maintainer-clean maintainer-clean-generic \
+	maintainer-clean-recursive mostlyclean mostlyclean-generic \
+	mostlyclean-recursive pdf pdf-am ps ps-am tags tags-recursive \
+	uninstall uninstall-am uninstall-info-am
+
+# Tell versions [3.59,3.63) of GNU make to not export all variables.
+# Otherwise a system limit (for SysV at least) may be exceeded.
+.NOEXPORT:

corpora/en/wordnet/doc/Makefile.am

@@ -0,0 +1 @@
+SUBDIRS = html man pdf ps

corpora/en/wordnet/doc/Makefile.in

@@ -0,0 +1,426 @@
+# Makefile.in generated by automake 1.9 from Makefile.am.
+# @configure_input@
+
+# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
+# 2003, 2004  Free Software Foundation, Inc.
+# This Makefile.in is free software; the Free Software Foundation
+# gives unlimited permission to copy and/or distribute it,
+# with or without modifications, as long as this notice is preserved.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
+# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+# PARTICULAR PURPOSE.
+
+@SET_MAKE@
+srcdir = @srcdir@
+top_srcdir = @top_srcdir@
+VPATH = @srcdir@
+pkgdatadir = $(datadir)/@PACKAGE@
+pkglibdir = $(libdir)/@PACKAGE@
+pkgincludedir = $(includedir)/@PACKAGE@
+top_builddir = ..
+am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd
+INSTALL = @INSTALL@
+install_sh_DATA = $(install_sh) -c -m 644
+install_sh_PROGRAM = $(install_sh) -c
+install_sh_SCRIPT = $(install_sh) -c
+INSTALL_HEADER = $(INSTALL_DATA)
+transform = $(program_transform_name)
+NORMAL_INSTALL = :
+PRE_INSTALL = :
+POST_INSTALL = :
+NORMAL_UNINSTALL = :
+PRE_UNINSTALL = :
+POST_UNINSTALL = :
+subdir = doc
+DIST_COMMON = $(srcdir)/Makefile.am $(srcdir)/Makefile.in
+ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
+am__aclocal_m4_deps = $(top_srcdir)/acinclude.m4 \
+	$(top_srcdir)/configure.ac
+am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
+	$(ACLOCAL_M4)
+mkinstalldirs = $(install_sh) -d
+CONFIG_HEADER = $(top_builddir)/config.h
+CONFIG_CLEAN_FILES =
+SOURCES =
+DIST_SOURCES =
+RECURSIVE_TARGETS = all-recursive check-recursive dvi-recursive \
+	html-recursive info-recursive install-data-recursive \
+	install-exec-recursive install-info-recursive \
+	install-recursive installcheck-recursive installdirs-recursive \
+	pdf-recursive ps-recursive uninstall-info-recursive \
+	uninstall-recursive
+ETAGS = etags
+CTAGS = ctags
+DIST_SUBDIRS = $(SUBDIRS)
+DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
+ACLOCAL = @ACLOCAL@
+AMDEP_FALSE = @AMDEP_FALSE@
+AMDEP_TRUE = @AMDEP_TRUE@
+AMTAR = @AMTAR@
+AUTOCONF = @AUTOCONF@
+AUTOHEADER = @AUTOHEADER@
+AUTOMAKE = @AUTOMAKE@
+AWK = @AWK@
+CC = @CC@
+CCDEPMODE = @CCDEPMODE@
+CFLAGS = @CFLAGS@
+CPP = @CPP@
+CPPFLAGS = @CPPFLAGS@
+CYGPATH_W = @CYGPATH_W@
+DEFS = @DEFS@
+DEPDIR = @DEPDIR@
+ECHO_C = @ECHO_C@
+ECHO_N = @ECHO_N@
+ECHO_T = @ECHO_T@
+EGREP = @EGREP@
+EXEEXT = @EXEEXT@
+INSTALL_DATA = @INSTALL_DATA@
+INSTALL_PROGRAM = @INSTALL_PROGRAM@
+INSTALL_SCRIPT = @INSTALL_SCRIPT@
+INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@
+LDFLAGS = @LDFLAGS@
+LIBOBJS = @LIBOBJS@
+LIBS = @LIBS@
+LTLIBOBJS = @LTLIBOBJS@
+MAKEINFO = @MAKEINFO@
+OBJEXT = @OBJEXT@
+PACKAGE = @PACKAGE@
+PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@
+PACKAGE_NAME = @PACKAGE_NAME@
+PACKAGE_STRING = @PACKAGE_STRING@
+PACKAGE_TARNAME = @PACKAGE_TARNAME@
+PACKAGE_VERSION = @PACKAGE_VERSION@
+PATH_SEPARATOR = @PATH_SEPARATOR@
+RANLIB = @RANLIB@
+SET_MAKE = @SET_MAKE@
+SHELL = @SHELL@
+STRIP = @STRIP@
+TCL_INCLUDE_SPEC = @TCL_INCLUDE_SPEC@
+TCL_LIB_SPEC = @TCL_LIB_SPEC@
+TK_LIBS = @TK_LIBS@
+TK_LIB_SPEC = @TK_LIB_SPEC@
+TK_PREFIX = @TK_PREFIX@
+TK_XINCLUDES = @TK_XINCLUDES@
+VERSION = @VERSION@
+ac_ct_CC = @ac_ct_CC@
+ac_ct_RANLIB = @ac_ct_RANLIB@
+ac_ct_STRIP = @ac_ct_STRIP@
+ac_prefix = @ac_prefix@
+am__fastdepCC_FALSE = @am__fastdepCC_FALSE@
+am__fastdepCC_TRUE = @am__fastdepCC_TRUE@
+am__include = @am__include@
+am__leading_dot = @am__leading_dot@
+am__quote = @am__quote@
+am__tar = @am__tar@
+am__untar = @am__untar@
+bindir = @bindir@
+build_alias = @build_alias@
+datadir = @datadir@
+exec_prefix = @exec_prefix@
+host_alias = @host_alias@
+includedir = @includedir@
+infodir = @infodir@
+install_sh = @install_sh@
+libdir = @libdir@
+libexecdir = @libexecdir@
+localstatedir = @localstatedir@
+mandir = @mandir@
+mkdir_p = @mkdir_p@
+oldincludedir = @oldincludedir@
+prefix = @prefix@
+program_transform_name = @program_transform_name@
+sbindir = @sbindir@
+sharedstatedir = @sharedstatedir@
+sysconfdir = @sysconfdir@
+target_alias = @target_alias@
+SUBDIRS = html man pdf ps
+all: all-recursive
+
+.SUFFIXES:
+$(srcdir)/Makefile.in:  $(srcdir)/Makefile.am  $(am__configure_deps)
+	@for dep in $?; do \
+	  case '$(am__configure_deps)' in \
+	    *$$dep*) \
+	      cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh \
+		&& exit 0; \
+	      exit 1;; \
+	  esac; \
+	done; \
+	echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu  doc/Makefile'; \
+	cd $(top_srcdir) && \
+	  $(AUTOMAKE) --gnu  doc/Makefile
+.PRECIOUS: Makefile
+Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status
+	@case '$?' in \
+	  *config.status*) \
+	    cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \
+	  *) \
+	    echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)'; \
+	    cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \
+	esac;
+
+$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+
+$(top_srcdir)/configure:  $(am__configure_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+$(ACLOCAL_M4):  $(am__aclocal_m4_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+uninstall-info-am:
+
+# This directory's subdirectories are mostly independent; you can cd
+# into them and run `make' without going through this Makefile.
+# To change the values of `make' variables: instead of editing Makefiles,
+# (1) if the variable is set in `config.status', edit `config.status'
+#     (which will cause the Makefiles to be regenerated when you run `make');
+# (2) otherwise, pass the desired values on the `make' command line.
+$(RECURSIVE_TARGETS):
+	@set fnord $$MAKEFLAGS; amf=$$2; \
+	dot_seen=no; \
+	target=`echo $@ | sed s/-recursive//`; \
+	list='$(SUBDIRS)'; for subdir in $$list; do \
+	  echo "Making $$target in $$subdir"; \
+	  if test "$$subdir" = "."; then \
+	    dot_seen=yes; \
+	    local_target="$$target-am"; \
+	  else \
+	    local_target="$$target"; \
+	  fi; \
+	  (cd $$subdir && $(MAKE) $(AM_MAKEFLAGS) $$local_target) \
+	   || case "$$amf" in *=*) exit 1;; *k*) fail=yes;; *) exit 1;; esac; \
+	done; \
+	if test "$$dot_seen" = "no"; then \
+	  $(MAKE) $(AM_MAKEFLAGS) "$$target-am" || exit 1; \
+	fi; test -z "$$fail"
+
+mostlyclean-recursive clean-recursive distclean-recursive \
+maintainer-clean-recursive:
+	@set fnord $$MAKEFLAGS; amf=$$2; \
+	dot_seen=no; \
+	case "$@" in \
+	  distclean-* | maintainer-clean-*) list='$(DIST_SUBDIRS)' ;; \
+	  *) list='$(SUBDIRS)' ;; \
+	esac; \
+	rev=''; for subdir in $$list; do \
+	  if test "$$subdir" = "."; then :; else \
+	    rev="$$subdir $$rev"; \
+	  fi; \
+	done; \
+	rev="$$rev ."; \
+	target=`echo $@ | sed s/-recursive//`; \
+	for subdir in $$rev; do \
+	  echo "Making $$target in $$subdir"; \
+	  if test "$$subdir" = "."; then \
+	    local_target="$$target-am"; \
+	  else \
+	    local_target="$$target"; \
+	  fi; \
+	  (cd $$subdir && $(MAKE) $(AM_MAKEFLAGS) $$local_target) \
+	   || case "$$amf" in *=*) exit 1;; *k*) fail=yes;; *) exit 1;; esac; \
+	done && test -z "$$fail"
+tags-recursive:
+	list='$(SUBDIRS)'; for subdir in $$list; do \
+	  test "$$subdir" = . || (cd $$subdir && $(MAKE) $(AM_MAKEFLAGS) tags); \
+	done
+ctags-recursive:
+	list='$(SUBDIRS)'; for subdir in $$list; do \
+	  test "$$subdir" = . || (cd $$subdir && $(MAKE) $(AM_MAKEFLAGS) ctags); \
+	done
+
+ID: $(HEADERS) $(SOURCES) $(LISP) $(TAGS_FILES)
+	list='$(SOURCES) $(HEADERS) $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	mkid -fID $$unique
+tags: TAGS
+
+TAGS: tags-recursive $(HEADERS) $(SOURCES)  $(TAGS_DEPENDENCIES) \
+		$(TAGS_FILES) $(LISP)
+	tags=; \
+	here=`pwd`; \
+	if ($(ETAGS) --etags-include --version) >/dev/null 2>&1; then \
+	  include_option=--etags-include; \
+	  empty_fix=.; \
+	else \
+	  include_option=--include; \
+	  empty_fix=; \
+	fi; \
+	list='$(SUBDIRS)'; for subdir in $$list; do \
+	  if test "$$subdir" = .; then :; else \
+	    test ! -f $$subdir/TAGS || \
+	      tags="$$tags $$include_option=$$here/$$subdir/TAGS"; \
+	  fi; \
+	done; \
+	list='$(SOURCES) $(HEADERS)  $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	if test -z "$(ETAGS_ARGS)$$tags$$unique"; then :; else \
+	  test -n "$$unique" || unique=$$empty_fix; \
+	  $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \
+	    $$tags $$unique; \
+	fi
+ctags: CTAGS
+CTAGS: ctags-recursive $(HEADERS) $(SOURCES)  $(TAGS_DEPENDENCIES) \
+		$(TAGS_FILES) $(LISP)
+	tags=; \
+	here=`pwd`; \
+	list='$(SOURCES) $(HEADERS)  $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	test -z "$(CTAGS_ARGS)$$tags$$unique" \
+	  || $(CTAGS) $(CTAGSFLAGS) $(AM_CTAGSFLAGS) $(CTAGS_ARGS) \
+	     $$tags $$unique
+
+GTAGS:
+	here=`$(am__cd) $(top_builddir) && pwd` \
+	  && cd $(top_srcdir) \
+	  && gtags -i $(GTAGS_ARGS) $$here
+
+distclean-tags:
+	-rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH tags
+
+distdir: $(DISTFILES)
+	@srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; \
+	topsrcdirstrip=`echo "$(top_srcdir)" | sed 's|.|.|g'`; \
+	list='$(DISTFILES)'; for file in $$list; do \
+	  case $$file in \
+	    $(srcdir)/*) file=`echo "$$file" | sed "s|^$$srcdirstrip/||"`;; \
+	    $(top_srcdir)/*) file=`echo "$$file" | sed "s|^$$topsrcdirstrip/|$(top_builddir)/|"`;; \
+	  esac; \
+	  if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \
+	  dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \
+	  if test "$$dir" != "$$file" && test "$$dir" != "."; then \
+	    dir="/$$dir"; \
+	    $(mkdir_p) "$(distdir)$$dir"; \
+	  else \
+	    dir=''; \
+	  fi; \
+	  if test -d $$d/$$file; then \
+	    if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \
+	      cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \
+	    fi; \
+	    cp -pR $$d/$$file $(distdir)$$dir || exit 1; \
+	  else \
+	    test -f $(distdir)/$$file \
+	    || cp -p $$d/$$file $(distdir)/$$file \
+	    || exit 1; \
+	  fi; \
+	done
+	list='$(DIST_SUBDIRS)'; for subdir in $$list; do \
+	  if test "$$subdir" = .; then :; else \
+	    test -d "$(distdir)/$$subdir" \
+	    || $(mkdir_p) "$(distdir)/$$subdir" \
+	    || exit 1; \
+	    distdir=`$(am__cd) $(distdir) && pwd`; \
+	    top_distdir=`$(am__cd) $(top_distdir) && pwd`; \
+	    (cd $$subdir && \
+	      $(MAKE) $(AM_MAKEFLAGS) \
+	        top_distdir="$$top_distdir" \
+	        distdir="$$distdir/$$subdir" \
+	        distdir) \
+	      || exit 1; \
+	  fi; \
+	done
+check-am: all-am
+check: check-recursive
+all-am: Makefile
+installdirs: installdirs-recursive
+installdirs-am:
+install: install-recursive
+install-exec: install-exec-recursive
+install-data: install-data-recursive
+uninstall: uninstall-recursive
+
+install-am: all-am
+	@$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am
+
+installcheck: installcheck-recursive
+install-strip:
+	$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
+	  install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
+	  `test -z '$(STRIP)' || \
+	    echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
+mostlyclean-generic:
+
+clean-generic:
+
+distclean-generic:
+	-test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES)
+
+maintainer-clean-generic:
+	@echo "This command is intended for maintainers to use"
+	@echo "it deletes files that may require special tools to rebuild."
+clean: clean-recursive
+
+clean-am: clean-generic mostlyclean-am
+
+distclean: distclean-recursive
+	-rm -f Makefile
+distclean-am: clean-am distclean-generic distclean-tags
+
+dvi: dvi-recursive
+
+dvi-am:
+
+html: html-recursive
+
+info: info-recursive
+
+info-am:
+
+install-data-am:
+
+install-exec-am:
+
+install-info: install-info-recursive
+
+install-man:
+
+installcheck-am:
+
+maintainer-clean: maintainer-clean-recursive
+	-rm -f Makefile
+maintainer-clean-am: distclean-am maintainer-clean-generic
+
+mostlyclean: mostlyclean-recursive
+
+mostlyclean-am: mostlyclean-generic
+
+pdf: pdf-recursive
+
+pdf-am:
+
+ps: ps-recursive
+
+ps-am:
+
+uninstall-am: uninstall-info-am
+
+uninstall-info: uninstall-info-recursive
+
+.PHONY: $(RECURSIVE_TARGETS) CTAGS GTAGS all all-am check check-am \
+	clean clean-generic clean-recursive ctags ctags-recursive \
+	distclean distclean-generic distclean-recursive distclean-tags \
+	distdir dvi dvi-am html html-am info info-am install \
+	install-am install-data install-data-am install-exec \
+	install-exec-am install-info install-info-am install-man \
+	install-strip installcheck installcheck-am installdirs \
+	installdirs-am maintainer-clean maintainer-clean-generic \
+	maintainer-clean-recursive mostlyclean mostlyclean-generic \
+	mostlyclean-recursive pdf pdf-am ps ps-am tags tags-recursive \
+	uninstall uninstall-am uninstall-info-am
+
+# Tell versions [3.59,3.63) of GNU make to not export all variables.
+# Otherwise a system limit (for SysV at least) may be exceeded.
+.NOEXPORT:

corpora/en/wordnet/doc/html/Makefile

@@ -0,0 +1,313 @@
+# Makefile.in generated by automake 1.9 from Makefile.am.
+# doc/html/Makefile.  Generated from Makefile.in by configure.
+
+# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
+# 2003, 2004  Free Software Foundation, Inc.
+# This Makefile.in is free software; the Free Software Foundation
+# gives unlimited permission to copy and/or distribute it,
+# with or without modifications, as long as this notice is preserved.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
+# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+# PARTICULAR PURPOSE.
+
+
+
+srcdir = .
+top_srcdir = ../..
+
+pkgdatadir = $(datadir)/WordNet
+pkglibdir = $(libdir)/WordNet
+pkgincludedir = $(includedir)/WordNet
+top_builddir = ../..
+am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd
+INSTALL = /usr/csl/bin/install -c
+install_sh_DATA = $(install_sh) -c -m 644
+install_sh_PROGRAM = $(install_sh) -c
+install_sh_SCRIPT = $(install_sh) -c
+INSTALL_HEADER = $(INSTALL_DATA)
+transform = $(program_transform_name)
+NORMAL_INSTALL = :
+PRE_INSTALL = :
+POST_INSTALL = :
+NORMAL_UNINSTALL = :
+PRE_UNINSTALL = :
+POST_UNINSTALL = :
+subdir = doc/html
+DIST_COMMON = $(srcdir)/Makefile.am $(srcdir)/Makefile.in
+ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
+am__aclocal_m4_deps = $(top_srcdir)/acinclude.m4 \
+	$(top_srcdir)/configure.ac
+am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
+	$(ACLOCAL_M4)
+mkinstalldirs = $(install_sh) -d
+CONFIG_HEADER = $(top_builddir)/config.h
+CONFIG_CLEAN_FILES =
+SOURCES =
+DIST_SOURCES =
+am__vpath_adj_setup = srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`;
+am__vpath_adj = case $$p in \
+    $(srcdir)/*) f=`echo "$$p" | sed "s|^$$srcdirstrip/||"`;; \
+    *) f=$$p;; \
+  esac;
+am__strip_dir = `echo $$p | sed -e 's|^.*/||'`;
+am__installdirs = "$(DESTDIR)$(htmldir)"
+htmlDATA_INSTALL = $(INSTALL_DATA)
+DATA = $(html_DATA)
+DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
+ACLOCAL = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run aclocal-1.9
+AMDEP_FALSE = #
+AMDEP_TRUE = 
+AMTAR = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run tar
+AUTOCONF = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run autoconf
+AUTOHEADER = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run autoheader
+AUTOMAKE = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run automake-1.9
+AWK = nawk
+CC = gcc
+CCDEPMODE = depmode=gcc3
+CFLAGS = -g -O2
+CPP = gcc -E
+CPPFLAGS = 
+CYGPATH_W = echo
+DEFS = -DHAVE_CONFIG_H
+DEPDIR = .deps
+ECHO_C = 
+ECHO_N = -n
+ECHO_T = 
+EGREP = egrep
+EXEEXT = 
+INSTALL_DATA = ${INSTALL} -m 644
+INSTALL_PROGRAM = ${INSTALL}
+INSTALL_SCRIPT = ${INSTALL}
+INSTALL_STRIP_PROGRAM = ${SHELL} $(install_sh) -c -s
+LDFLAGS = 
+LIBOBJS = 
+LIBS = 
+LTLIBOBJS = 
+MAKEINFO = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run makeinfo
+OBJEXT = o
+PACKAGE = WordNet
+PACKAGE_BUGREPORT = wordnet@princeton.edu
+PACKAGE_NAME = WordNet
+PACKAGE_STRING = WordNet 3.0
+PACKAGE_TARNAME = wordnet
+PACKAGE_VERSION = 3.0
+PATH_SEPARATOR = :
+RANLIB = ranlib
+SET_MAKE = 
+SHELL = /bin/bash
+STRIP = 
+TCL_INCLUDE_SPEC = -I/usr/csl/include
+TCL_LIB_SPEC = -L/usr/csl/lib -ltcl8.4
+TK_LIBS = -L/usr/openwin/lib -lX11 -ldl  -lpthread -lsocket -lnsl -lm
+TK_LIB_SPEC = -L/usr/csl/lib -ltk8.4
+TK_PREFIX = /usr/csl
+TK_XINCLUDES = -I/usr/openwin/include
+VERSION = 3.0
+ac_ct_CC = gcc
+ac_ct_RANLIB = ranlib
+ac_ct_STRIP = 
+ac_prefix = /usr/local/WordNet-3.0
+am__fastdepCC_FALSE = #
+am__fastdepCC_TRUE = 
+am__include = include
+am__leading_dot = .
+am__quote = 
+am__tar = ${AMTAR} chof - "$$tardir"
+am__untar = ${AMTAR} xf -
+bindir = ${exec_prefix}/bin
+build_alias = 
+datadir = ${prefix}/share
+exec_prefix = ${prefix}
+host_alias = 
+includedir = ${prefix}/include
+infodir = ${prefix}/info
+install_sh = /people/wn/src/Release/3.0/Unix/install-sh
+libdir = ${exec_prefix}/lib
+libexecdir = ${exec_prefix}/libexec
+localstatedir = ${prefix}/var
+mandir = ${prefix}/man
+mkdir_p = $(install_sh) -d
+oldincludedir = /usr/include
+prefix = /usr/local/WordNet-3.0
+program_transform_name = s,x,x,
+sbindir = ${exec_prefix}/sbin
+sharedstatedir = ${prefix}/com
+sysconfdir = ${prefix}/etc
+target_alias = 
+htmldir = $(prefix)/doc/html
+html_DATA = binsrch.3WN.html cntlist.5WN.html grind.1WN.html lexnames.5WN.html morph.3WN.html morphy.7WN.html senseidx.5WN.html uniqbeg.7WN.html wn.1WN.html wnb.1WN.html wndb.5WN.html wngloss.7WN.html wngroups.7WN.html wninput.5WN.html wnintro.1WN.html wnintro.3WN.html wnintro.5WN.html wnintro.7WN.html wnlicens.7WN.html wnpkgs.7WN.html wnsearch.3WN.html wnstats.7WN.html wnutil.3WN.html
+all: all-am
+
+.SUFFIXES:
+$(srcdir)/Makefile.in:  $(srcdir)/Makefile.am  $(am__configure_deps)
+	@for dep in $?; do \
+	  case '$(am__configure_deps)' in \
+	    *$$dep*) \
+	      cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh \
+		&& exit 0; \
+	      exit 1;; \
+	  esac; \
+	done; \
+	echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu  doc/html/Makefile'; \
+	cd $(top_srcdir) && \
+	  $(AUTOMAKE) --gnu  doc/html/Makefile
+.PRECIOUS: Makefile
+Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status
+	@case '$?' in \
+	  *config.status*) \
+	    cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \
+	  *) \
+	    echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)'; \
+	    cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \
+	esac;
+
+$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+
+$(top_srcdir)/configure:  $(am__configure_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+$(ACLOCAL_M4):  $(am__aclocal_m4_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+uninstall-info-am:
+install-htmlDATA: $(html_DATA)
+	@$(NORMAL_INSTALL)
+	test -z "$(htmldir)" || $(mkdir_p) "$(DESTDIR)$(htmldir)"
+	@list='$(html_DATA)'; for p in $$list; do \
+	  if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \
+	  f=$(am__strip_dir) \
+	  echo " $(htmlDATA_INSTALL) '$$d$$p' '$(DESTDIR)$(htmldir)/$$f'"; \
+	  $(htmlDATA_INSTALL) "$$d$$p" "$(DESTDIR)$(htmldir)/$$f"; \
+	done
+
+uninstall-htmlDATA:
+	@$(NORMAL_UNINSTALL)
+	@list='$(html_DATA)'; for p in $$list; do \
+	  f=$(am__strip_dir) \
+	  echo " rm -f '$(DESTDIR)$(htmldir)/$$f'"; \
+	  rm -f "$(DESTDIR)$(htmldir)/$$f"; \
+	done
+tags: TAGS
+TAGS:
+
+ctags: CTAGS
+CTAGS:
+
+
+distdir: $(DISTFILES)
+	@srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; \
+	topsrcdirstrip=`echo "$(top_srcdir)" | sed 's|.|.|g'`; \
+	list='$(DISTFILES)'; for file in $$list; do \
+	  case $$file in \
+	    $(srcdir)/*) file=`echo "$$file" | sed "s|^$$srcdirstrip/||"`;; \
+	    $(top_srcdir)/*) file=`echo "$$file" | sed "s|^$$topsrcdirstrip/|$(top_builddir)/|"`;; \
+	  esac; \
+	  if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \
+	  dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \
+	  if test "$$dir" != "$$file" && test "$$dir" != "."; then \
+	    dir="/$$dir"; \
+	    $(mkdir_p) "$(distdir)$$dir"; \
+	  else \
+	    dir=''; \
+	  fi; \
+	  if test -d $$d/$$file; then \
+	    if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \
+	      cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \
+	    fi; \
+	    cp -pR $$d/$$file $(distdir)$$dir || exit 1; \
+	  else \
+	    test -f $(distdir)/$$file \
+	    || cp -p $$d/$$file $(distdir)/$$file \
+	    || exit 1; \
+	  fi; \
+	done
+check-am: all-am
+check: check-am
+all-am: Makefile $(DATA)
+installdirs:
+	for dir in "$(DESTDIR)$(htmldir)"; do \
+	  test -z "$$dir" || $(mkdir_p) "$$dir"; \
+	done
+install: install-am
+install-exec: install-exec-am
+install-data: install-data-am
+uninstall: uninstall-am
+
+install-am: all-am
+	@$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am
+
+installcheck: installcheck-am
+install-strip:
+	$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
+	  install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
+	  `test -z '$(STRIP)' || \
+	    echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
+mostlyclean-generic:
+
+clean-generic:
+
+distclean-generic:
+	-test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES)
+
+maintainer-clean-generic:
+	@echo "This command is intended for maintainers to use"
+	@echo "it deletes files that may require special tools to rebuild."
+clean: clean-am
+
+clean-am: clean-generic mostlyclean-am
+
+distclean: distclean-am
+	-rm -f Makefile
+distclean-am: clean-am distclean-generic
+
+dvi: dvi-am
+
+dvi-am:
+
+html: html-am
+
+info: info-am
+
+info-am:
+
+install-data-am: install-htmlDATA
+
+install-exec-am:
+
+install-info: install-info-am
+
+install-man:
+
+installcheck-am:
+
+maintainer-clean: maintainer-clean-am
+	-rm -f Makefile
+maintainer-clean-am: distclean-am maintainer-clean-generic
+
+mostlyclean: mostlyclean-am
+
+mostlyclean-am: mostlyclean-generic
+
+pdf: pdf-am
+
+pdf-am:
+
+ps: ps-am
+
+ps-am:
+
+uninstall-am: uninstall-htmlDATA uninstall-info-am
+
+.PHONY: all all-am check check-am clean clean-generic distclean \
+	distclean-generic distdir dvi dvi-am html html-am info info-am \
+	install install-am install-data install-data-am install-exec \
+	install-exec-am install-htmlDATA install-info install-info-am \
+	install-man install-strip installcheck installcheck-am \
+	installdirs maintainer-clean maintainer-clean-generic \
+	mostlyclean mostlyclean-generic pdf pdf-am ps ps-am uninstall \
+	uninstall-am uninstall-htmlDATA uninstall-info-am
+
+# Tell versions [3.59,3.63) of GNU make to not export all variables.
+# Otherwise a system limit (for SysV at least) may be exceeded.
+.NOEXPORT:

corpora/en/wordnet/doc/html/Makefile.am

@@ -0,0 +1,2 @@
+htmldir = $(prefix)/doc/html
+html_DATA = binsrch.3WN.html cntlist.5WN.html grind.1WN.html lexnames.5WN.html morph.3WN.html morphy.7WN.html senseidx.5WN.html uniqbeg.7WN.html wn.1WN.html wnb.1WN.html wndb.5WN.html wngloss.7WN.html wngroups.7WN.html wninput.5WN.html wnintro.1WN.html wnintro.3WN.html wnintro.5WN.html wnintro.7WN.html wnlicens.7WN.html wnpkgs.7WN.html wnsearch.3WN.html wnstats.7WN.html wnutil.3WN.html

corpora/en/wordnet/doc/html/Makefile.in

@@ -0,0 +1,313 @@
+# Makefile.in generated by automake 1.9 from Makefile.am.
+# @configure_input@
+
+# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
+# 2003, 2004  Free Software Foundation, Inc.
+# This Makefile.in is free software; the Free Software Foundation
+# gives unlimited permission to copy and/or distribute it,
+# with or without modifications, as long as this notice is preserved.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
+# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+# PARTICULAR PURPOSE.
+
+@SET_MAKE@
+
+srcdir = @srcdir@
+top_srcdir = @top_srcdir@
+VPATH = @srcdir@
+pkgdatadir = $(datadir)/@PACKAGE@
+pkglibdir = $(libdir)/@PACKAGE@
+pkgincludedir = $(includedir)/@PACKAGE@
+top_builddir = ../..
+am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd
+INSTALL = @INSTALL@
+install_sh_DATA = $(install_sh) -c -m 644
+install_sh_PROGRAM = $(install_sh) -c
+install_sh_SCRIPT = $(install_sh) -c
+INSTALL_HEADER = $(INSTALL_DATA)
+transform = $(program_transform_name)
+NORMAL_INSTALL = :
+PRE_INSTALL = :
+POST_INSTALL = :
+NORMAL_UNINSTALL = :
+PRE_UNINSTALL = :
+POST_UNINSTALL = :
+subdir = doc/html
+DIST_COMMON = $(srcdir)/Makefile.am $(srcdir)/Makefile.in
+ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
+am__aclocal_m4_deps = $(top_srcdir)/acinclude.m4 \
+	$(top_srcdir)/configure.ac
+am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
+	$(ACLOCAL_M4)
+mkinstalldirs = $(install_sh) -d
+CONFIG_HEADER = $(top_builddir)/config.h
+CONFIG_CLEAN_FILES =
+SOURCES =
+DIST_SOURCES =
+am__vpath_adj_setup = srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`;
+am__vpath_adj = case $$p in \
+    $(srcdir)/*) f=`echo "$$p" | sed "s|^$$srcdirstrip/||"`;; \
+    *) f=$$p;; \
+  esac;
+am__strip_dir = `echo $$p | sed -e 's|^.*/||'`;
+am__installdirs = "$(DESTDIR)$(htmldir)"
+htmlDATA_INSTALL = $(INSTALL_DATA)
+DATA = $(html_DATA)
+DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
+ACLOCAL = @ACLOCAL@
+AMDEP_FALSE = @AMDEP_FALSE@
+AMDEP_TRUE = @AMDEP_TRUE@
+AMTAR = @AMTAR@
+AUTOCONF = @AUTOCONF@
+AUTOHEADER = @AUTOHEADER@
+AUTOMAKE = @AUTOMAKE@
+AWK = @AWK@
+CC = @CC@
+CCDEPMODE = @CCDEPMODE@
+CFLAGS = @CFLAGS@
+CPP = @CPP@
+CPPFLAGS = @CPPFLAGS@
+CYGPATH_W = @CYGPATH_W@
+DEFS = @DEFS@
+DEPDIR = @DEPDIR@
+ECHO_C = @ECHO_C@
+ECHO_N = @ECHO_N@
+ECHO_T = @ECHO_T@
+EGREP = @EGREP@
+EXEEXT = @EXEEXT@
+INSTALL_DATA = @INSTALL_DATA@
+INSTALL_PROGRAM = @INSTALL_PROGRAM@
+INSTALL_SCRIPT = @INSTALL_SCRIPT@
+INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@
+LDFLAGS = @LDFLAGS@
+LIBOBJS = @LIBOBJS@
+LIBS = @LIBS@
+LTLIBOBJS = @LTLIBOBJS@
+MAKEINFO = @MAKEINFO@
+OBJEXT = @OBJEXT@
+PACKAGE = @PACKAGE@
+PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@
+PACKAGE_NAME = @PACKAGE_NAME@
+PACKAGE_STRING = @PACKAGE_STRING@
+PACKAGE_TARNAME = @PACKAGE_TARNAME@
+PACKAGE_VERSION = @PACKAGE_VERSION@
+PATH_SEPARATOR = @PATH_SEPARATOR@
+RANLIB = @RANLIB@
+SET_MAKE = @SET_MAKE@
+SHELL = @SHELL@
+STRIP = @STRIP@
+TCL_INCLUDE_SPEC = @TCL_INCLUDE_SPEC@
+TCL_LIB_SPEC = @TCL_LIB_SPEC@
+TK_LIBS = @TK_LIBS@
+TK_LIB_SPEC = @TK_LIB_SPEC@
+TK_PREFIX = @TK_PREFIX@
+TK_XINCLUDES = @TK_XINCLUDES@
+VERSION = @VERSION@
+ac_ct_CC = @ac_ct_CC@
+ac_ct_RANLIB = @ac_ct_RANLIB@
+ac_ct_STRIP = @ac_ct_STRIP@
+ac_prefix = @ac_prefix@
+am__fastdepCC_FALSE = @am__fastdepCC_FALSE@
+am__fastdepCC_TRUE = @am__fastdepCC_TRUE@
+am__include = @am__include@
+am__leading_dot = @am__leading_dot@
+am__quote = @am__quote@
+am__tar = @am__tar@
+am__untar = @am__untar@
+bindir = @bindir@
+build_alias = @build_alias@
+datadir = @datadir@
+exec_prefix = @exec_prefix@
+host_alias = @host_alias@
+includedir = @includedir@
+infodir = @infodir@
+install_sh = @install_sh@
+libdir = @libdir@
+libexecdir = @libexecdir@
+localstatedir = @localstatedir@
+mandir = @mandir@
+mkdir_p = @mkdir_p@
+oldincludedir = @oldincludedir@
+prefix = @prefix@
+program_transform_name = @program_transform_name@
+sbindir = @sbindir@
+sharedstatedir = @sharedstatedir@
+sysconfdir = @sysconfdir@
+target_alias = @target_alias@
+htmldir = $(prefix)/doc/html
+html_DATA = binsrch.3WN.html cntlist.5WN.html grind.1WN.html lexnames.5WN.html morph.3WN.html morphy.7WN.html senseidx.5WN.html uniqbeg.7WN.html wn.1WN.html wnb.1WN.html wndb.5WN.html wngloss.7WN.html wngroups.7WN.html wninput.5WN.html wnintro.1WN.html wnintro.3WN.html wnintro.5WN.html wnintro.7WN.html wnlicens.7WN.html wnpkgs.7WN.html wnsearch.3WN.html wnstats.7WN.html wnutil.3WN.html
+all: all-am
+
+.SUFFIXES:
+$(srcdir)/Makefile.in:  $(srcdir)/Makefile.am  $(am__configure_deps)
+	@for dep in $?; do \
+	  case '$(am__configure_deps)' in \
+	    *$$dep*) \
+	      cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh \
+		&& exit 0; \
+	      exit 1;; \
+	  esac; \
+	done; \
+	echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu  doc/html/Makefile'; \
+	cd $(top_srcdir) && \
+	  $(AUTOMAKE) --gnu  doc/html/Makefile
+.PRECIOUS: Makefile
+Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status
+	@case '$?' in \
+	  *config.status*) \
+	    cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \
+	  *) \
+	    echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)'; \
+	    cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \
+	esac;
+
+$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+
+$(top_srcdir)/configure:  $(am__configure_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+$(ACLOCAL_M4):  $(am__aclocal_m4_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+uninstall-info-am:
+install-htmlDATA: $(html_DATA)
+	@$(NORMAL_INSTALL)
+	test -z "$(htmldir)" || $(mkdir_p) "$(DESTDIR)$(htmldir)"
+	@list='$(html_DATA)'; for p in $$list; do \
+	  if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \
+	  f=$(am__strip_dir) \
+	  echo " $(htmlDATA_INSTALL) '$$d$$p' '$(DESTDIR)$(htmldir)/$$f'"; \
+	  $(htmlDATA_INSTALL) "$$d$$p" "$(DESTDIR)$(htmldir)/$$f"; \
+	done
+
+uninstall-htmlDATA:
+	@$(NORMAL_UNINSTALL)
+	@list='$(html_DATA)'; for p in $$list; do \
+	  f=$(am__strip_dir) \
+	  echo " rm -f '$(DESTDIR)$(htmldir)/$$f'"; \
+	  rm -f "$(DESTDIR)$(htmldir)/$$f"; \
+	done
+tags: TAGS
+TAGS:
+
+ctags: CTAGS
+CTAGS:
+
+
+distdir: $(DISTFILES)
+	@srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; \
+	topsrcdirstrip=`echo "$(top_srcdir)" | sed 's|.|.|g'`; \
+	list='$(DISTFILES)'; for file in $$list; do \
+	  case $$file in \
+	    $(srcdir)/*) file=`echo "$$file" | sed "s|^$$srcdirstrip/||"`;; \
+	    $(top_srcdir)/*) file=`echo "$$file" | sed "s|^$$topsrcdirstrip/|$(top_builddir)/|"`;; \
+	  esac; \
+	  if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \
+	  dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \
+	  if test "$$dir" != "$$file" && test "$$dir" != "."; then \
+	    dir="/$$dir"; \
+	    $(mkdir_p) "$(distdir)$$dir"; \
+	  else \
+	    dir=''; \
+	  fi; \
+	  if test -d $$d/$$file; then \
+	    if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \
+	      cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \
+	    fi; \
+	    cp -pR $$d/$$file $(distdir)$$dir || exit 1; \
+	  else \
+	    test -f $(distdir)/$$file \
+	    || cp -p $$d/$$file $(distdir)/$$file \
+	    || exit 1; \
+	  fi; \
+	done
+check-am: all-am
+check: check-am
+all-am: Makefile $(DATA)
+installdirs:
+	for dir in "$(DESTDIR)$(htmldir)"; do \
+	  test -z "$$dir" || $(mkdir_p) "$$dir"; \
+	done
+install: install-am
+install-exec: install-exec-am
+install-data: install-data-am
+uninstall: uninstall-am
+
+install-am: all-am
+	@$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am
+
+installcheck: installcheck-am
+install-strip:
+	$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
+	  install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
+	  `test -z '$(STRIP)' || \
+	    echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
+mostlyclean-generic:
+
+clean-generic:
+
+distclean-generic:
+	-test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES)
+
+maintainer-clean-generic:
+	@echo "This command is intended for maintainers to use"
+	@echo "it deletes files that may require special tools to rebuild."
+clean: clean-am
+
+clean-am: clean-generic mostlyclean-am
+
+distclean: distclean-am
+	-rm -f Makefile
+distclean-am: clean-am distclean-generic
+
+dvi: dvi-am
+
+dvi-am:
+
+html: html-am
+
+info: info-am
+
+info-am:
+
+install-data-am: install-htmlDATA
+
+install-exec-am:
+
+install-info: install-info-am
+
+install-man:
+
+installcheck-am:
+
+maintainer-clean: maintainer-clean-am
+	-rm -f Makefile
+maintainer-clean-am: distclean-am maintainer-clean-generic
+
+mostlyclean: mostlyclean-am
+
+mostlyclean-am: mostlyclean-generic
+
+pdf: pdf-am
+
+pdf-am:
+
+ps: ps-am
+
+ps-am:
+
+uninstall-am: uninstall-htmlDATA uninstall-info-am
+
+.PHONY: all all-am check check-am clean clean-generic distclean \
+	distclean-generic distdir dvi dvi-am html html-am info info-am \
+	install install-am install-data install-data-am install-exec \
+	install-exec-am install-htmlDATA install-info install-info-am \
+	install-man install-strip installcheck installcheck-am \
+	installdirs maintainer-clean maintainer-clean-generic \
+	mostlyclean mostlyclean-generic pdf pdf-am ps ps-am uninstall \
+	uninstall-am uninstall-htmlDATA uninstall-info-am
+
+# Tell versions [3.59,3.63) of GNU make to not export all variables.
+# Otherwise a system limit (for SysV at least) may be exceeded.
+.NOEXPORT:

corpora/en/wordnet/doc/html/binsrch.3WN.html

@@ -0,0 +1,78 @@
+<!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>BINSRCH(3WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+bin_search, copyfile, replace_line, insert_line  
+<H2><A NAME="sect1" HREF="#toc1">SYNOPSIS </A></H2>
+<P>
+<B>char *bin_search(char 
+*key, FILE *fp); </B> <P>
+<B>void copyfile(FILE *fromfp, FILE *tofp); </B> <P>
+<B>char *replace_line(char 
+*new_line, char *key, FILE *fp); </B> <P>
+<B>char *insert_line(char *new_line, char 
+*key, FILE *fp); </B>  
+<H2><A NAME="sect2" HREF="#toc2">DESCRIPTION </A></H2>
+<P>
+The WordNet library contains several general 
+purpose functions for performing a binary search and modifying sorted 
+files. <P>
+<B>bin_search()</B> is the primary binary search algorithm to search for 
+<I>key </I> as the first item on a line in the file pointed to by <I>fp </I>.  The delimiter 
+between the key and the rest of the fields on the line, if any, must be 
+a space.  A pointer to a static variable containing the entire line is 
+returned. <FONT SIZE=-1><B>NULL </B></FONT>
+  is returned if a match is not found. <P>
+The remaining functions 
+are not used by WordNet, and are only briefly described. <P>
+<B>copyfile()</B> copies 
+the contents of one file to another. <P>
+<B>replace_line()</B> replaces a line in 
+a file having searchkey <I>key </I> with the contents of <I>new_line </I>. It returns 
+the original line or <FONT SIZE=-1><B>NULL </B></FONT>
+  in case of error. <P>
+<B>insert_line()</B> finds the proper 
+place to insert the contents of <I>new_line </I>, having searchkey <I>key </I> in the 
+sorted file pointed to by <I>fp </I>. It returns <FONT SIZE=-1><B>NULL </B></FONT>
+  if a line with this searchkey 
+is already in the file.  
+<H2><A NAME="sect3" HREF="#toc3">NOTES </A></H2>
+The maximum length of <I>key </I> is 1024. <P>
+ The 
+maximum line length in a file is 25K. <P>
+ If there are no additional fields 
+after the search key, the key must be followed by at least one space before 
+the newline character.  
+<H2><A NAME="sect4" HREF="#toc4">SEE ALSO </A></H2>
+<B><A HREF="wnintro.3WN.html">wnintro</B>(3WN)</A>
+, <B><A HREF="morph.3WN.html">morph</B>(3WN)</A>
+, <B><A HREF="wnsearch.3WN.html">wnsearch</B>(3WN)</A>
+, 
+<B><A HREF="wnutil.3WN.html">wnutil</B>(3WN)</A>
+, <B><A HREF="wnintro.5WN.html">wnintro</B>(5WN)</A>
+.  
+<H2><A NAME="sect5" HREF="#toc5">WARNINGS </A></H2>
+<B>binsearch() </B> returns a pointer to 
+a static character buffer. The returned string should be copied by the 
+caller if the results need to be saved, as a subsequent call will replace 
+the contents of the static buffer. <P>
+ <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">SYNOPSIS</A></LI>
+<LI><A NAME="toc2" HREF="#sect2">DESCRIPTION</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">NOTES</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">SEE ALSO</A></LI>
+<LI><A NAME="toc5" HREF="#sect5">WARNINGS</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/cntlist.5WN.html

@@ -0,0 +1,125 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>CNTLIST(5WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+cntlist - file listing number of times each tagged sense occurs 
+in a semantic concordance, sorted most to least frequently tagged <P>
+ cntlist.rev 
+- file listing number of times each tagged sense occurs in a semantic concordance, 
+sorted by sense key  
+<H2><A NAME="sect1" HREF="#toc1">DESCRIPTION </A></H2>
+A cntlist file for a semantic concordance 
+lists the number of times each semantically tagged sense occurs in the 
+concordance and its sense number in the WordNet database.  Each line in 
+the file corresponds to a sense in the WordNet database to which at least 
+one semantic tag points.  Only senses that are tagged in a concordance 
+are in the concordance's cntlist file. <P>
+  
+<H3><A NAME="sect2" HREF="#toc2">WordNet Database <I>cntlist </I> File 
+</A></H3>
+In the WordNet database, words are assigned sense numbers based on frequency 
+of use in semantically tagged corpora.  The cntlist file used by <B><A HREF="grind.1WN.html">grind</B>(1WN)<B></B></A>
+ 
+to build the WordNet database and assign the sense numbers is a union 
+of the cntlist files from the various semantic concordances that were 
+formerly released by Princeton University.  This combined cntlist file 
+is provided with the WordNet package and is found in the <B>WNSEARCHDIR </B> 
+directory. <P>
+ The <I>cntlist.rev </I> file is used at run-time by the WordNet library 
+code and browser interfaces to print in the output display the number 
+of times each sense has been tagged.  
+<H3><A NAME="sect3" HREF="#toc3">File Format </A></H3>
+Each line in a cntlist 
+file contains information for one sense.  The file is ordered from most 
+to least frequently tagged sense.  The fields are separated by one space, 
+and each line is terminated with a newline character.  Senses having the 
+same <I>tag_cnt </I> value are listed in reverse alphabetical order of the <I>lemma 
+</I> field of the <I>sense_key </I>. <P>
+ Each line in <B>cntlist </B> is of the form: <P>
+  <blockquote><I>tag_cnt&nbsp;&nbsp;sense_key&nbsp;&nbsp;sense_number 
+</I>  </blockquote>
+<P>
+ where <I>tag_cnt </I> is the decimal number of times the sense is tagged in 
+the corresponding semantic concordance.  <I>sense_key </I> is a WordNet sense 
+encoding and <I>sense_number </I> is a WordNet sense number as described in <P>
+ 
+The <I>cntlist.rev </I> file contains the same fields described above, in the 
+following order: <P>
+  <blockquote><I>sense_key&nbsp;&nbsp;sense_number&nbsp;&nbsp;tag_cnt </I>  </blockquote>
+<P>
+  
+<H2><A NAME="sect4" HREF="#toc4">NOTES </A></H2>
+Princeton 
+no longer maintains or releases the Semantic Concordance files.  The <I>cntlist 
+</I> file used to order the senses in WordNet 3.0 was generated from the Semantic 
+Concordance files at the point that they were last updated in 2001.  In 
+general, the order of senses presented usually reflects what the user 
+would expect, however sense ordering is now less reliable than in prior 
+releases and should not be construed as an accurate indicator of frequency 
+of use.  
+<H2><A NAME="sect5" HREF="#toc5">ENVIRONMENT VARIABLES (UNIX) </A></H2>
+
+<DL>
+
+<DT><B>WNHOME</B>  </DT>
+<DD>Base directory for WordNet. 
+ Default is <B>/usr/local/WordNet-3.0 </B>. </DD>
+
+<DT><B>WNSEARCHDIR</B>  </DT>
+<DD>Directory in which the 
+WordNet database has been installed.   Default is <B>WNHOME/dict </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect6" HREF="#toc6">REGISTRY 
+(WINDOWS) </A></H2>
+
+<DL>
+
+<DT><B>HKEY_LOCAL_MACHINE\SOFTWARE\WordNet\3.0\WNHome</B>  </DT>
+<DD>Base directory for 
+WordNet.  Default is <B>C:\Program&nbsp;Files\WordNet\3.0 </B>. </DD>
+
+<DT><B>HKEY_CURRENT_USER\SOFTWARE\WordNet\3.0\wnres</B> 
+ </DT>
+<DD>User's default browser options. </DD>
+</DL>
+ 
+<H2><A NAME="sect7" HREF="#toc7">FILES </A></H2>
+
+<DL>
+
+<DT><B>cntlist, cntlist.rev</B>  </DT>
+<DD>file of combined 
+semantic concordance <B>cntlist </B> files.  Used to assign sense numbers in WordNet 
+database </DD>
+</DL>
+ 
+<H2><A NAME="sect8" HREF="#toc8">SEE ALSO </A></H2>
+<B><A HREF="grind.1WN.html">grind</B>(1WN)</A>
+, <B><A HREF="wnintro.5WN.html">wnintro</B>(5WN)</A>
+, <B><A HREF="senseidx.5WN.html">senseidx</B>(5WN)</A>
+. <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">DESCRIPTION</A></LI>
+<UL>
+<LI><A NAME="toc2" HREF="#sect2">WordNet Database cntlist  File</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">File Format</A></LI>
+</UL>
+<LI><A NAME="toc4" HREF="#sect4">NOTES</A></LI>
+<LI><A NAME="toc5" HREF="#sect5">ENVIRONMENT VARIABLES (UNIX)</A></LI>
+<LI><A NAME="toc6" HREF="#sect6">REGISTRY (WINDOWS)</A></LI>
+<LI><A NAME="toc7" HREF="#sect7">FILES</A></LI>
+<LI><A NAME="toc8" HREF="#sect8">SEE ALSO</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/grind.1WN.html

@@ -0,0 +1,195 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>GRIND(1) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+grind - process WordNet lexicographer files  
+<H2><A NAME="sect1" HREF="#toc1">SYNOPSIS </A></H2>
+<B>grind </B> [ <B>-v 
+</B> ] [ <B>-s </B> ] [ <B>-L </B><I>logfile </I> ] [ <B>-a </B> ] [ <B>-d </B> ] [ <B>-i </B> ] [ <B>-o </B> ] [ <B>-n </B> ] <I>filename </I> 
+[ <I>filename </I>... ]  
+<H2><A NAME="sect2" HREF="#toc2">DESCRIPTION </A></H2>
+<B>grind() </B> processes WordNet lexicographer files, 
+producing database files suitable for use with the WordNet search and 
+interface code and other applications.  The syntactic and structural integrity 
+of the input files is verified.  Warnings and errors are reported via <B>stderr 
+</B> and a run-time log is produced on <B>stdout </B>.  A database is generated only 
+if there are no errors.  
+<H3><A NAME="sect3" HREF="#toc3">Input Files </A></H3>
+Input files correspond to the syntactic 
+categories implemented in WordNet - <B>noun</B>, <B></B> <B>verb</B>, <B></B> <B>adjective</B> and <B></B> <B>adverb</B>. 
+Each input lexicographer file consists of a list of synonym sets (<I>synsets 
+</I>) for one part of speech.  Although the basic synset syntax is the same 
+for all of the parts of speech, some parts of the syntax only apply to 
+a particular part of speech.  See <B><A HREF="wninput.5WN.html">wninput</B>(5WN)<B></B></A>
+ for a description of the 
+input file format. <P>
+ Each <I>filename </I> specified is of the form: <P>
+  <blockquote>  </blockquote>
+<P>
+ where 
+<I>pathname </I> is optional and <I>pos </I> is either <B>noun</B>, <B></B> <B>verb</B>, <B></B> <B>adj</B> or <B></B> <B>adv</B>. <I>suffix 
+</I> may be used to separate groups of synsets into different files, for example 
+<B>noun.animal </B> and <B>noun.plant </B>.  One or more input files, in any combination 
+of syntactic categories, may be specified.  See <B><A HREF="lexnames.5WN.html">lexnames</B>(5WN)</A>
+ for a list 
+of the lexicographer files used to build the complete WordNet database. 
+ 
+<H3><A NAME="sect4" HREF="#toc4">Output Files </A></H3>
+<B>grind() </B> produces the following output files: <P>
+  <TABLE BORDER=0>
+ <TR> <TD ALIGN=CENTER><B>Filename 
+</B></TD> <TD ALIGN=CENTER>Description  </TD> </TR>
+ <TR>  <TR> <TD ALIGN=LEFT><B>index.<I>pos </I></B> </TD> <TD ALIGN=LEFT>Index file for each syntactic category </TD> 
+</TR>
+ <TR> <TD ALIGN=LEFT><B>data.<I>pos </I></B> </TD> <TD ALIGN=LEFT>Data file for each syntactic category </TD> </TR>
+ <TR> <TD ALIGN=LEFT><B>index.sense </B> </TD> <TD ALIGN=LEFT>Sense 
+index </TD> </TR>
+ </TABLE>
+<P>
+ See  <B><A HREF="wndb.5WN.html">wndb</B>(5WN)<B></B></A>
+ for a description of the database file formats. 
+<P>
+ Each time <B>grind() </B> is run, any existing database files are overwritten 
+with the database files generated from the specified input files.  If no 
+input files from a syntactic category are specified, the corresponding 
+database files are not overwritten.  
+<H3><A NAME="sect5" HREF="#toc5">Sense Numbers </A></H3>
+Senses are generally 
+ordered from most to least frequently used, with the most common sense 
+numbered <B>1 </B>.  Frequency of use is determined by the number of times a sense 
+is tagged in the various semantic concordance texts.  Senses that are not 
+semantically tagged follow the ordered senses in an arbitrary order.   
+Note that this ordering is only an estimate based on usage in a small 
+corpus. <P>
+ The <I>tagsense_cnt </I> field for each entry in the <B>index.<I>pos </I></B> files 
+indicates how many of the senses in the list have been tagged. <P>
+ The <B>cntlist 
+</B> file provided with the database lists the number of times each sense 
+is tagged in the semantic concordances. <B>grind() </B> uses the data from <B>cntlist 
+</B> to order the senses of each word.  When the <B>index </B>.<I>pos </I> files are generated, 
+the <I>synset_offset </I>s are output in sense number order, with sense 1 first 
+in the list.  Senses with the same number of semantic tags are assigned 
+unique but consecutive sense numbers.  The WordNet <FONT SIZE=-1><B>OVERVIEW </B></FONT>
+  search displays 
+all senses of the specified word, in all syntactic categories, and indicates 
+which of the senses are represented in the semantically tagged texts.  
+
+<H2><A NAME="sect6" HREF="#toc6">OPTIONS </A></H2>
+
+<DL>
+
+<DT><B>-v</B>  </DT>
+<DD>Verify integrity of input without generating database. </DD>
+
+<DT><B>-s</B>  </DT>
+<DD>Suppress 
+generation of warning messages.  Usually <B>grind </B> is run with this option 
+until all syntactic and structural errors are corrected since the warning 
+messages may make it difficult to spot error messages. </DD>
+
+<DT><B>-L</B><I>logfile</I>  </DT>
+<DD>Write 
+all messages to <I>logfile </I> instead of <B>stderr </B>. </DD>
+
+<DT><B>-a</B>  </DT>
+<DD>Generate statistical report 
+on input files processed. </DD>
+
+<DT><B>-d</B>  </DT>
+<DD>Generate distribution of senses by string 
+length report on input files processed.  </DD>
+
+<DT><B>-i</B>  </DT>
+<DD>Generate sense index file. </DD>
+
+<DT><B>-o</B> 
+ </DT>
+<DD>Order senses using <B>cntlist </B>. </DD>
+
+<DT><B>-n</B>  </DT>
+<DD>Generate nominalization (derivational 
+morphology) links in database. </DD>
+
+<DT><I>filename</I>  </DT>
+<DD>Input file of the form described 
+in  <FONT SIZE=-1><B>Input </B></FONT>
+  </DD>
+</DL>
+ 
+<H2><A NAME="sect7" HREF="#toc7">FILES </A></H2>
+
+<DL>
+
+<DT><B><I>pos </I>.*</B>  </DT>
+<DD>lexicographer files to use to build database 
+</DD>
+
+<DT><B>cntlist</B>  </DT>
+<DD>file of combined semantic concordance <B>cntlist </B> files.  Used to 
+assign sense numbers in WordNet database </DD>
+</DL>
+ 
+<H2><A NAME="sect8" HREF="#toc8">SEE ALSO </A></H2>
+<B><A HREF="cntlist.5WN.html">cntlist</B>(5WN)</A>
+, <B><A HREF="lexnames.5WN.html">lexnames</B>(5WN)</A>
+, 
+<B><A HREF="senseidx.5WN.html">senseidx</B>(5WN)</A>
+, <B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+, <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+, <B><A HREF="uniqbeg.7WN.html">uniqbeg</B>(7WN)</A>
+, <B><A HREF="wngloss.7WN.html">wngloss</B>(7WN)</A>
+.  
+<H2><A NAME="sect9" HREF="#toc9">DIAGNOSTICS 
+</A></H2>
+Exit status is normally 0. Exit status is -1 if non-specific error occurs. 
+If syntactic or structural errors exist, exit status is number of errors 
+detected. 
+<DL>
+
+<DT><B>usage: grind [-v] [-s] [-Llogfile] [-a ] [-d] [-i] [-o] [-n] filename 
+[filename...]</B>  </DT>
+<DD>Invalid options were specified on the command line. </DD>
+
+<DT><B>No input 
+files processed.</B>  </DT>
+<DD>None of the filenames specified were of the appropriate 
+form. </DD>
+
+<DT><B><I>n </I> syntactic errors found.</B>  </DT>
+<DD>Syntax errors were found while parsing 
+the input files. </DD>
+
+<DT><B><I>n </I> structural errors found.</B>  </DT>
+<DD>Pointer errors were found 
+that could not be automatically corrected. </DD>
+</DL>
+ 
+<H2><A NAME="sect10" HREF="#toc10">BUGS </A></H2>
+Please report bugs to 
+<B>wordnet@princeton.edu </B>. <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">SYNOPSIS</A></LI>
+<LI><A NAME="toc2" HREF="#sect2">DESCRIPTION</A></LI>
+<UL>
+<LI><A NAME="toc3" HREF="#sect3">Input Files</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">Output Files</A></LI>
+<LI><A NAME="toc5" HREF="#sect5">Sense Numbers</A></LI>
+</UL>
+<LI><A NAME="toc6" HREF="#sect6">OPTIONS</A></LI>
+<LI><A NAME="toc7" HREF="#sect7">FILES</A></LI>
+<LI><A NAME="toc8" HREF="#sect8">SEE ALSO</A></LI>
+<LI><A NAME="toc9" HREF="#sect9">DIAGNOSTICS</A></LI>
+<LI><A NAME="toc10" HREF="#sect10">BUGS</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/lexnames.5WN.html

@@ -0,0 +1,195 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>LEXNAMES(5WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+List of WordNet lexicographer file names and numbers  
+<H2><A NAME="sect1" HREF="#toc1">DESCRIPTION 
+</A></H2>
+During WordNet development synsets are organized into forty-five lexicographer 
+files based on syntactic category and logical groupings. <B><A HREF="grind.1WN.html">grind</B>(1WN)</A>
+ processes 
+these files and produces a database suitable for use with the WordNet 
+library, interface code, and other applications.  The format of the lexicographer 
+files is described in <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+. <P>
+ A file number corresponds to each 
+lexicographer file.  File numbers are encoded in several parts of the WordNet 
+system as an efficient way to indicate a lexicographer file name.  The 
+file <B>lexnames </B> lists the mapping between file names and numbers, and can 
+be used by programs or end users to correlate the two.  
+<H3><A NAME="sect2" HREF="#toc2">File Format </A></H3>
+Each 
+line in <B>lexnames </B> contains 3 tab separated fields, and is terminated with 
+a newline character.  The first field is the two digit decimal integer 
+file number.  (The first file in the list is numbered <B>00 </B>.)  The second 
+field is the name of the lexicographer file that is represented by that 
+number, and the third field is an integer that indicates the syntactic 
+category of the synsets contained in the file. This is simply a shortcut 
+for programs and scripts, since the syntactic category is also part of 
+the lexicographer file's name.  
+<H3><A NAME="sect3" HREF="#toc3">Syntactic Category </A></H3>
+The syntactic category 
+field is encoded as follows: <P>
+  <blockquote><B>1 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;NOUN <BR>
+ <B>2 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;VERB <BR>
+ <B>3 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADJECTIVE <BR>
+ <B>4 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADVERB <BR>
+ 
+ </blockquote>
+ 
+<H3><A NAME="sect4" HREF="#toc4">Lexicographer Files </A></H3>
+The names of the lexicographer files and their corresponding 
+file numbers are listed below along with a brief description each file's 
+contents.  <P>
+  <blockquote> <TABLE BORDER=0>
+ <TR> <TD ALIGN=LEFT><B>File Number </B> </TD> <TD ALIGN=LEFT><B>Name </B> </TD> <TD ALIGN=LEFT><B>Contents </B> </TD> </TR>
+ <TR>  <TR> <TD ALIGN=LEFT>00 </TD> <TD ALIGN=LEFT>adj.all </TD> <TD ALIGN=LEFT>all adjective 
+clusters </TD> </TR>
+ <TR> <TD ALIGN=LEFT>01 </TD> <TD ALIGN=LEFT>adj.pert </TD> <TD ALIGN=LEFT>relational adjectives (pertainyms) </TD> </TR>
+ <TR> <TD ALIGN=LEFT>02 </TD> <TD ALIGN=LEFT>adv.all 
+</TD> <TD ALIGN=LEFT>all adverbs </TD> </TR>
+ <TR> <TD ALIGN=LEFT>03 </TD> <TD ALIGN=LEFT>noun.Tops </TD> <TD ALIGN=LEFT>unique beginner for nouns </TD> </TR>
+ <TR> <TD ALIGN=LEFT>04 </TD> <TD ALIGN=LEFT>noun.act 
+</TD> <TD ALIGN=LEFT>nouns denoting acts or actions  </TD> </TR>
+ <TR> <TD ALIGN=LEFT>05 </TD> <TD ALIGN=LEFT>noun.animal </TD> <TD ALIGN=LEFT>nouns denoting animals 
+</TD> </TR>
+ <TR> <TD ALIGN=LEFT>06 </TD> <TD ALIGN=LEFT>noun.artifact </TD> <TD ALIGN=LEFT>nouns denoting man-made objects </TD> </TR>
+ <TR> <TD ALIGN=LEFT>07 </TD> <TD ALIGN=LEFT>noun.attribute 
+</TD> <TD ALIGN=LEFT>nouns denoting attributes of people and objects   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>08 </TD> <TD ALIGN=LEFT>noun.body </TD> <TD ALIGN=LEFT>nouns 
+denoting body parts   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>09 </TD> <TD ALIGN=LEFT>noun.cognition </TD> <TD ALIGN=LEFT>nouns denoting cognitive processes 
+and contents </TD> </TR>
+ <TR> <TD ALIGN=LEFT>10 </TD> <TD ALIGN=LEFT>noun.communication </TD> <TD ALIGN=LEFT>nouns denoting communicative processes 
+and contents   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>11 </TD> <TD ALIGN=LEFT>noun.event </TD> <TD ALIGN=LEFT>nouns denoting natural events   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>12 
+</TD> <TD ALIGN=LEFT>noun.feeling </TD> <TD ALIGN=LEFT>nouns denoting feelings and emotions   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>13 </TD> <TD ALIGN=LEFT>noun.food </TD> 
+<TD ALIGN=LEFT>nouns denoting foods and drinks   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>14 </TD> <TD ALIGN=LEFT>noun.group </TD> <TD ALIGN=LEFT>nouns denoting groupings 
+of people or objects   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>15 </TD> <TD ALIGN=LEFT>noun.location </TD> <TD ALIGN=LEFT>nouns denoting spatial position 
+ </TD> </TR>
+ <TR> <TD ALIGN=LEFT>16 </TD> <TD ALIGN=LEFT>noun.motive </TD> <TD ALIGN=LEFT>nouns denoting goals   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>17 </TD> <TD ALIGN=LEFT>noun.object </TD> <TD ALIGN=LEFT>nouns denoting 
+natural objects (not man-made)   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>18 </TD> <TD ALIGN=LEFT>noun.person   </TD> <TD ALIGN=LEFT>nouns denoting people 
+</TD> </TR>
+ <TR> <TD ALIGN=LEFT>19 </TD> <TD ALIGN=LEFT>noun.phenomenon </TD> <TD ALIGN=LEFT>nouns denoting natural phenomena   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>20 </TD> <TD ALIGN=LEFT>noun.plant 
+</TD> <TD ALIGN=LEFT>nouns denoting plants  </TD> </TR>
+ <TR> <TD ALIGN=LEFT>21 </TD> <TD ALIGN=LEFT>noun.possession </TD> <TD ALIGN=LEFT>nouns denoting possession 
+and transfer of possession   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>22 </TD> <TD ALIGN=LEFT>noun.process </TD> <TD ALIGN=LEFT>nouns denoting natural 
+processes   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>23 </TD> <TD ALIGN=LEFT>noun.quantity </TD> <TD ALIGN=LEFT>nouns denoting quantities and units of 
+measure   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>24 </TD> <TD ALIGN=LEFT>noun.relation </TD> <TD ALIGN=LEFT>nouns denoting relations between people 
+or things or ideas   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>25 </TD> <TD ALIGN=LEFT>noun.shape </TD> <TD ALIGN=LEFT>nouns denoting two and three dimensional 
+shapes   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>26 </TD> <TD ALIGN=LEFT>noun.state </TD> <TD ALIGN=LEFT>nouns denoting stable states of affairs   </TD> 
+</TR>
+ <TR> <TD ALIGN=LEFT>27 </TD> <TD ALIGN=LEFT>noun.substance </TD> <TD ALIGN=LEFT>nouns denoting substances   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>28 </TD> <TD ALIGN=LEFT>noun.time </TD> <TD ALIGN=LEFT>nouns 
+denoting time and temporal relations   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>29 </TD> <TD ALIGN=LEFT>verb.body </TD> <TD ALIGN=LEFT>verbs of grooming, 
+dressing and bodily care   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>30 </TD> <TD ALIGN=LEFT>verb.change </TD> <TD ALIGN=LEFT>verbs of size, temperature 
+change, intensifying, etc.   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>31 </TD> <TD ALIGN=LEFT>verb.cognition </TD> <TD ALIGN=LEFT>verbs of thinking, judging, 
+analyzing, doubting   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>32 </TD> <TD ALIGN=LEFT>verb.communication </TD> <TD ALIGN=LEFT>verbs of telling, asking, 
+ordering, singing   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>33 </TD> <TD ALIGN=LEFT>verb.competition </TD> <TD ALIGN=LEFT>verbs of fighting, athletic 
+activities   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>34 </TD> <TD ALIGN=LEFT>verb.consumption </TD> <TD ALIGN=LEFT>verbs of eating and drinking   </TD> </TR>
+ 
+<TR> <TD ALIGN=LEFT>35 </TD> <TD ALIGN=LEFT>verb.contact </TD> <TD ALIGN=LEFT>verbs of touching, hitting, tying, digging   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>36 </TD> 
+<TD ALIGN=LEFT>verb.creation </TD> <TD ALIGN=LEFT>verbs of sewing, baking, painting, performing   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>37 </TD> <TD ALIGN=LEFT>verb.emotion 
+</TD> <TD ALIGN=LEFT>verbs of feeling   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>38 </TD> <TD ALIGN=LEFT>verb.motion </TD> <TD ALIGN=LEFT>verbs of walking, flying, swimming 
+  </TD> </TR>
+ <TR> <TD ALIGN=LEFT>39 </TD> <TD ALIGN=LEFT>verb.perception </TD> <TD ALIGN=LEFT>verbs of seeing, hearing, feeling  </TD> </TR>
+ <TR> <TD ALIGN=LEFT>40 </TD> <TD ALIGN=LEFT>verb.possession 
+</TD> <TD ALIGN=LEFT>verbs of buying, selling, owning   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>41 </TD> <TD ALIGN=LEFT>verb.social </TD> <TD ALIGN=LEFT>verbs of political 
+and social activities and events   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>42 </TD> <TD ALIGN=LEFT>verb.stative </TD> <TD ALIGN=LEFT>verbs of being, 
+having, spatial relations   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>43 </TD> <TD ALIGN=LEFT>verb.weather </TD> <TD ALIGN=LEFT>verbs of raining, snowing, 
+thawing, thundering   </TD> </TR>
+ <TR> <TD ALIGN=LEFT>44 </TD> <TD ALIGN=LEFT>adj.ppl </TD> <TD ALIGN=LEFT>participial adjectives </TD> </TR>
+ </TABLE>
+ </blockquote>
+ 
+<H2><A NAME="sect5" HREF="#toc5">NOTES 
+</A></H2>
+The lexicographer files are not included in the WordNet database package. 
+ 
+<H2><A NAME="sect6" HREF="#toc6">ENVIRONMENT VARIABLES (UNIX) </A></H2>
+
+<DL>
+
+<DT><B>WNHOME</B>  </DT>
+<DD>Base directory for WordNet.  Default 
+is <B>/usr/local/WordNet-3.0 </B>. </DD>
+
+<DT><B>WNSEARCHDIR</B>  </DT>
+<DD>Directory in which the WordNet database 
+has been installed.   Default is <B>WNHOME/dict </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect7" HREF="#toc7">REGISTRY (WINDOWS) </A></H2>
+
+<DL>
+
+<DT><B>HKEY_LOCAL_MACHINE\SOFTWARE\WordNet\3.0\WNHome</B> 
+ </DT>
+<DD>Base directory for WordNet.  Default is <B>C:\Program&nbsp;Files\WordNet\3.0 </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect8" HREF="#toc8">FILES 
+</A></H2>
+
+<DL>
+
+<DT><B>lexnames</B>  </DT>
+<DD>list of lexicographer file names and numbers </DD>
+</DL>
+ 
+<H2><A NAME="sect9" HREF="#toc9">SEE ALSO </A></H2>
+<B><A HREF="grind.1WN.html">grind</B>(1WN)</A>
+, 
+<B><A HREF="wnintro.5WN.html">wnintro</B>(5WN)</A>
+, <B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+, <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+. <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">DESCRIPTION</A></LI>
+<UL>
+<LI><A NAME="toc2" HREF="#sect2">File Format</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">Syntactic Category</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">Lexicographer Files</A></LI>
+</UL>
+<LI><A NAME="toc5" HREF="#sect5">NOTES</A></LI>
+<LI><A NAME="toc6" HREF="#sect6">ENVIRONMENT VARIABLES (UNIX)</A></LI>
+<LI><A NAME="toc7" HREF="#sect7">REGISTRY (WINDOWS)</A></LI>
+<LI><A NAME="toc8" HREF="#sect8">FILES</A></LI>
+<LI><A NAME="toc9" HREF="#sect9">SEE ALSO</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/morph.3WN.html

@@ -0,0 +1,109 @@
+<!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>MORPH(3WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+morphinit, re_morphinit, morphstr, morphword  
+<H2><A NAME="sect1" HREF="#toc1">SYNOPSIS </A></H2>
+<P>
+<B>#include 
+"wn.h" </B> <P>
+<B>int morphinit(void); </B> <P>
+<B>int re_morphinit(void); </B> <P>
+<B>char *morphstr(char 
+*origstr, int pos); </B> <P>
+<B>char *morphword(char *word, int pos); </B>  
+<H2><A NAME="sect2" HREF="#toc2">DESCRIPTION 
+</A></H2>
+<P>
+The WordNet morphological processor, Morphy, is accessed through these 
+functions: <P>
+<B>morphinit()</B> is used to open the exception list files.  It returns 
+<B>0 </B> if successful, <B>-1 </B> otherwise.  The exception list files must be opened 
+before <B>morphstr() </B> or <B>morphword()</B> are called. <P>
+<B>re_morphinit()</B> is used to 
+close the exception list files and reopen them, and is used exclusively 
+for WordNet development.  Return codes are as described above. <P>
+<B>morphstr()</B> 
+is the basic user interface to Morphy.  It tries to find the base form 
+(lemma) of the word or collocation <I>origstr </I> in the specified <I>pos </I>.  The 
+first call (with <I>origstr </I> specified) returns a pointer to the first base 
+form found.  Subsequent calls requesting base forms of the same string 
+must be made with the first argument of <FONT SIZE=-1><B>NULL. </B></FONT>
+  When no more base forms 
+for <I>origstr </I> can be found, <FONT SIZE=-1><B>NULL </B></FONT>
+  is returned.  Note that <B>morphstr() </B> returns 
+a pointer to a static character buffer.  A subsequent call to <B>morphstr() 
+</B> with a new string (instead of <B>NULL </B>) will overwrite the string pointed 
+to by a previous call.  Users should copy the returned string into a local 
+buffer, or use the C library function <B>strdup </B> to duplicate the returned 
+string into a <I>malloc'd </I> buffer. <P>
+<B>morphword()</B> tries to find the base form 
+of <I>word </I> in the specified <I>pos </I>. This function is called by <B>morphstr()</B> for 
+each individual word in a collocation. Note that <B>morphword() </B> returns a 
+pointer to a static character buffer.  A subsequent call to <B>morphword() 
+</B>  will overwrite the string pointed to by a previous call.  Users should 
+copy the returned string into a local buffer, or use the C library function 
+<B>strdup </B> to duplicate the returned string into a <I>malloc'd </I> buffer.  
+<H2><A NAME="sect3" HREF="#toc3">NOTES 
+</A></H2>
+<B>morphinit()</B> is called by  <B>wninit() </B> and is not intended to be called directly 
+by an application. Applications wishing to use WordNet and/or the morphological 
+functions must call <B>wninit() </B> at the start of the program.  See <B><A HREF="wnutil.3WN.html">wnutil</B>(3WN)</A>
+ 
+for more information. <P>
+ <I>origstr </I> may be either a word or a collocation formed 
+by joining individual words with underscore characters (<B>_ </B>). <P>
+ Usually only 
+<B>morphstr() </B> is called from applications, as it works on both words and 
+collocations. <P>
+ <I>pos </I> must be one of the following: <P>
+  <blockquote><B>1 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;NOUN <BR>
+ <B>2 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;VERB <BR>
+ <B>3 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADJECTIVE 
+<BR>
+ <B>4 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADVERB <BR>
+ <B>5 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADJECTIVE_SATELLITE <BR>
+  </blockquote>
+<P>
+ If  <FONT SIZE=-1><B>ADJECTIVE_SATELLITE </B></FONT>
+  is passed, 
+it is treated by <B>morphstr() </B> as <FONT SIZE=-1><B>ADJECTIVE. </B></FONT>
+   
+<H2><A NAME="sect4" HREF="#toc4">SEE ALSO </A></H2>
+<B><A HREF="wnintro.3WN.html">wnintro</B>(3WN)</A>
+, <B><A HREF="wnsearch.3WN.html">wnsearch</B>(3WN)</A>
+, 
+<B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+, <B><A HREF="morphy.7WN.html">morphy</B>(7WN)</A>
+. <P>
+  
+<H2><A NAME="sect5" HREF="#toc5">WARNINGS </A></H2>
+Passing an invalid part of speech will 
+result in a core dump. <P>
+ The WordNet database files must be open to use 
+<B>morphstr() </B> or <B>morphword().  <P>
+  </B>
+<H2><A NAME="sect6" HREF="#toc6">BUGS </A></H2>
+Morphy will allow non-words to be converted 
+to words, if they follow one of the rules described above.  For example, 
+it will happily convert <B>plantes </B> to <B>plants </B>. <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">SYNOPSIS</A></LI>
+<LI><A NAME="toc2" HREF="#sect2">DESCRIPTION</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">NOTES</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">SEE ALSO</A></LI>
+<LI><A NAME="toc5" HREF="#sect5">WARNINGS</A></LI>
+<LI><A NAME="toc6" HREF="#sect6">BUGS</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/morphy.7WN.html

@@ -0,0 +1,221 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>MORPHY(7WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+morphy - discussion of WordNet's morphological processing  
+<H2><A NAME="sect1" HREF="#toc1">DESCRIPTION 
+</A></H2>
+Although only base forms of words are usually stored in WordNet, searches 
+may be done on inflected forms.  A set of morphology functions, Morphy, 
+is applied to the search string to generate a form that is present in 
+WordNet. <P>
+ Morphology in WordNet uses two types of processes to try to convert 
+the string passed into one that can be found in the WordNet database. There 
+are lists of inflectional endings, based on syntactic category, that can 
+be detached from individual words in an attempt to find a form of the 
+word that is in WordNet.  There are also exception list files, one for 
+each syntactic category, in which a search for an inflected form is done. 
+ Morphy tries to use these two processes in an intelligent manner to translate 
+the string passed to the base form found in WordNet.  Morphy first checks 
+for exceptions, then uses the rules of detachment.  The Morphy functions 
+are not independent from WordNet. After each transformation, WordNet is 
+searched for the resulting string in the syntactic category specified. 
+<P>
+ The Morphy functions are passed a string and a syntactic category.  A 
+string is either a single word or a collocation.  Since some words, such 
+as <B>axes </B> can have more than one base form (<B>axe </B> and <B>axis </B>), Morphy works 
+in the following manner.  The first time that Morphy is called with a specific 
+string, it returns a base form. For each subsequent call to Morphy made 
+with a  <FONT SIZE=-1><B>NULL </B></FONT>
+  string argument, Morphy returns another base form.  Whenever 
+Morphy cannot perform a transformation, whether on the first call for 
+a word or subsequent calls, <FONT SIZE=-1><B>NULL </B></FONT>
+  is returned.  A transformation to a 
+valid English string will return  <FONT SIZE=-1><B>NULL </B></FONT>
+  if the base form of the string 
+is not in WordNet. <P>
+ The morphological functions are found in the WordNet 
+library.  See <B><A HREF="morph.3WN.html">morph</B>(3WN)</A>
+ for information on using these functions.    
+<H3><A NAME="sect2" HREF="#toc2">Rules 
+of Detachment </A></H3>
+The following table shows the rules of detachment used by 
+Morphy.  If a word ends with one of the suffixes, it is stripped from the 
+word and the corresponding ending is added.  Then WordNet is searched for 
+the resulting string.  No rules are applicable to adverbs. <P>
+  <TABLE BORDER=0>
+ <TR> <TD ALIGN=CENTER><B>POS </B> </TD> <TD ALIGN=CENTER><B>Suffix 
+</B> </TD> <TD ALIGN=CENTER><B>Ending </B> </TD> </TR>
+ <TR>  <TR> <TD ALIGN=LEFT>NOUN </TD> <TD ALIGN=LEFT>"s" </TD> <TD ALIGN=LEFT>"" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>NOUN </TD> <TD ALIGN=LEFT>"ses" </TD> <TD ALIGN=LEFT>"s" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>NOUN </TD> <TD ALIGN=LEFT>"xes" </TD> <TD ALIGN=LEFT>"x" </TD> 
+</TR>
+ <TR> <TD ALIGN=LEFT>NOUN </TD> <TD ALIGN=LEFT>"zes" </TD> <TD ALIGN=LEFT>"z" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>NOUN </TD> <TD ALIGN=LEFT>"ches" </TD> <TD ALIGN=LEFT>"ch" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>NOUN </TD> <TD ALIGN=LEFT>"shes" </TD> <TD ALIGN=LEFT>"sh" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>NOUN 
+</TD> <TD ALIGN=LEFT>"men" </TD> <TD ALIGN=LEFT>"man" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>NOUN </TD> <TD ALIGN=LEFT>"ies" </TD> <TD ALIGN=LEFT>"y" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>VERB </TD> <TD ALIGN=LEFT>"s" </TD> <TD ALIGN=LEFT>"" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>VERB </TD> <TD ALIGN=LEFT>"ies" </TD> <TD ALIGN=LEFT>"y" 
+</TD> </TR>
+ <TR> <TD ALIGN=LEFT>VERB </TD> <TD ALIGN=LEFT>"es" </TD> <TD ALIGN=LEFT>"e" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>VERB </TD> <TD ALIGN=LEFT>"es" </TD> <TD ALIGN=LEFT>"" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>VERB </TD> <TD ALIGN=LEFT>"ed" </TD> <TD ALIGN=LEFT>"e" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>VERB </TD> <TD ALIGN=LEFT>"ed" 
+</TD> <TD ALIGN=LEFT>"" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>VERB </TD> <TD ALIGN=LEFT>"ing" </TD> <TD ALIGN=LEFT>"e" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>VERB </TD> <TD ALIGN=LEFT>"ing" </TD> <TD ALIGN=LEFT>"" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>ADJ </TD> <TD ALIGN=LEFT>"er" </TD> <TD ALIGN=LEFT>"" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>ADJ </TD> <TD ALIGN=LEFT>"est" 
+</TD> <TD ALIGN=LEFT>"" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>ADJ </TD> <TD ALIGN=LEFT>"er" </TD> <TD ALIGN=LEFT>"e" </TD> </TR>
+ <TR> <TD ALIGN=LEFT>ADJ </TD> <TD ALIGN=LEFT>"est" </TD> <TD ALIGN=LEFT>"e" </TD> </TR>
+ </TABLE>
+ 
+<H3><A NAME="sect3" HREF="#toc3">Exception Lists </A></H3>
+There is one 
+exception list file for each syntactic category.  The exception lists contain 
+the morphological transformations for strings that are not regular and 
+therefore cannot be processed in an algorithmic manner.  Each line of an 
+exception list contains an inflected form of a word or collocation, followed 
+by one or more base forms.  The list is kept in alphabetical order and 
+a binary search is used to find words in these lists.  See <B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+ for 
+information on the format of the exception list files.  
+<H3><A NAME="sect4" HREF="#toc4">Single Words </A></H3>
+In 
+general, single words are relatively easy to process.  Morphy first looks 
+for the word in the exception list.  If it is found the first base form 
+is returned.  Subsequent calls with a <FONT SIZE=-1><B>NULL </B></FONT>
+  argument return additional 
+base forms, if present.  A <FONT SIZE=-1><B>NULL </B></FONT>
+  is returned when there are no more base 
+forms of the word. <P>
+ If the word is not found in the exception list corresponding 
+to the syntactic category, an algorithmic process using the rules of detachment 
+looks for a matching suffix.  If a matching suffix is found, a corresponding 
+ending is applied (sometimes this ending is a <FONT SIZE=-1><B>NULL </B></FONT>
+  string, so in effect 
+the suffix is removed from the word), and WordNet is consulted to see 
+if the resulting word is found in the desired part of speech.  
+<H3><A NAME="sect5" HREF="#toc5">Collocations 
+</A></H3>
+As opposed to single words, collocations can be quite difficult to transform 
+into a base form that is present in WordNet.  In general, only base forms 
+of words, even those comprising collocations, are stored in WordNet, such 
+as <B>attorney&nbsp;general </B>.  Transforming the collocation <B>attorneys&nbsp;general </B> 
+is then simply a matter of finding the base forms of the individual words 
+comprising the collocation. This usually works for nouns, therefore non-conforming 
+nouns, such as <B>customs&nbsp;duty </B> are presently entered in the noun exception 
+list. <P>
+ Verb collocations that contain prepositions, such as <B>ask&nbsp;for&nbsp;it 
+</B>, are more difficult.  As with single words, the exception list is searched 
+first.  If the collocation is not found, special code in Morphy determines 
+whether a verb collocation includes a preposition. If it does, a function 
+is called to try to find the base form in the following manner.  It is 
+assumed that the first word in the collocation is a verb and that the 
+last word is a noun.  The algorithm then builds a search string with the 
+base forms of the verb and noun, leaving the remainder of the collocation 
+(usually just the preposition, but more words may be involved) in the 
+middle.  For example, passed <B>asking&nbsp;for&nbsp;it </B>, the database search would 
+be performed with <B>ask&nbsp;for&nbsp;it </B>, which is found in WordNet, and therefore 
+returned from Morphy.  If a verb collocation does not contain a preposition, 
+then the base form of each word in the collocation is found and WordNet 
+is searched for the resulting string.  
+<H3><A NAME="sect6" HREF="#toc6">Hyphenation </A></H3>
+Hyphenation also presents 
+special difficulties when searching WordNet. It is often a subjective decision 
+as to whether a word is hyphenated, joined as one word, or is a collocation 
+of several words, and which of the various forms are entered into WordNet. 
+ When Morphy breaks a string into "words", it looks for both spaces and 
+hyphens as delimiters.  It also looks for periods in strings and removes 
+them if an exact match is not found.  A search for an abbreviation like 
+<B>oct. </B> return the synset for <B>{&nbsp;October,&nbsp;Oct&nbsp;} </B>.  Not every pattern of hyphenated 
+and collocated string is searched for properly, so it may be advantageous 
+to specify several search strings if the results of a search attempt seem 
+incomplete.  
+<H3><A NAME="sect7" HREF="#toc7">Special Processing for nouns ending with 'ful' </A></H3>
+Morphy contains 
+code that searches for nouns ending with <B>ful </B> and performs a transformation 
+on the substring preceeding it.  It then appends 'ful' back onto the resulting 
+string and returns it. For example, if passed the nouns <B>boxesful </B>, it will 
+return <B>boxful </B>.  
+<H2><A NAME="sect8" HREF="#toc8">BUGS </A></H2>
+Since many noun collocations contains prepositions, 
+such as <B>line&nbsp;of&nbsp;products </B>, an algorithm similar to that used for verbs 
+should be written for nouns.  In the present scheme, if Morphy is passed 
+<B>lines&nbsp;of&nbsp;products </B>, the search string becomes <B>line&nbsp;of&nbsp;product </B>, which 
+is not in WordNet <P>
+ Morphy will allow non-words to be converted to words, 
+if they follow one of the rules described above.  For example, it will 
+happily convert <B>plantes </B> to <B>plants </B>.  
+<H2><A NAME="sect9" HREF="#toc9">ENVIRONMENT VARIABLES (UNIX) </A></H2>
+
+<DL>
+
+<DT><B>WNHOME</B> 
+ </DT>
+<DD>Base directory for WordNet.  Default is <B>/usr/local/WordNet-3.0 </B>. </DD>
+
+<DT><B>WNSEARCHDIR</B> 
+ </DT>
+<DD>Directory in which the WordNet database has been installed.   Default 
+is <B>WNHOME/dict </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect10" HREF="#toc10">REGISTRY (WINDOWS) </A></H2>
+
+<DL>
+
+<DT><B>HKEY_LOCAL_MACHINE\SOFTWARE\WordNet\3.0\WNHome</B> 
+ </DT>
+<DD>Base directory for WordNet.  Default is <B>C:\Program&nbsp;Files\WordNet\3.0 </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect11" HREF="#toc11">FILES 
+</A></H2>
+
+<DL>
+
+<DT><B><I>pos </I>.exc</B>  </DT>
+<DD>morphology exception lists </DD>
+</DL>
+ 
+<H2><A NAME="sect12" HREF="#toc12">SEE ALSO </A></H2>
+<B><A HREF="wn.1WN.html">wn</B>(1WN)</A>
+, <B><A HREF="wnb.1WN.html">wnb</B>(1WN)</A>
+, <B><A HREF="binsrch.3WN.html">binsrch</B>(3WN)</A>
+, 
+<B><A HREF="morph.3WN.html">morph</B>(3WN)</A>
+, <B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+, <B><A HREF="wninput.7WN.html">wninput</B>(7WN)</A>
+. <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">DESCRIPTION</A></LI>
+<UL>
+<LI><A NAME="toc2" HREF="#sect2">Rules of Detachment</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">Exception Lists</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">Single Words</A></LI>
+<LI><A NAME="toc5" HREF="#sect5">Collocations</A></LI>
+<LI><A NAME="toc6" HREF="#sect6">Hyphenation</A></LI>
+<LI><A NAME="toc7" HREF="#sect7">Special Processing for nouns ending with 'ful'</A></LI>
+</UL>
+<LI><A NAME="toc8" HREF="#sect8">BUGS</A></LI>
+<LI><A NAME="toc9" HREF="#sect9">ENVIRONMENT VARIABLES (UNIX)</A></LI>
+<LI><A NAME="toc10" HREF="#sect10">REGISTRY (WINDOWS)</A></LI>
+<LI><A NAME="toc11" HREF="#sect11">FILES</A></LI>
+<LI><A NAME="toc12" HREF="#sect12">SEE ALSO</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/prologdb.5WN.html

@@ -0,0 +1,318 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>PROLOGDB(5WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+wn_pl - description of Prolog database files  
+<H2><A NAME="sect1" HREF="#toc1">DESCRIPTION </A></H2>
+The files 
+<B>wn_ </B><I>* </I><B>.pl </B> contain the WordNet database in a prolog-readable format.  A prolog 
+interface to WordNet is not implemented. <P>
+ The prolog database is very large 
+and may take many minutes to load into the Prolog workspace.  A separate 
+file has been created for each WordNet relation giving the user the ability 
+to load only those parts of the database that they are interested. <P>
+ See 
+<B>FILES </B>, below, for a list of the database files and <B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+ and <B><A HREF="wninput.5WN.html">wninput</B>(5WN)<B></B></A>
+ 
+for detailed descriptions of the various WordNet relations (referred to 
+as <I>operators </I> in this manual page).  
+<H3><A NAME="sect2" HREF="#toc2">File Format </A></H3>
+Each prolog database file 
+contains information corresponding to the synsets and word senses contained 
+in the WordNet database.  In the prolog version of the database, the <I>synset_id 
+</I>s (defined below) are used as unique synset identifiers. <P>
+ Each line of 
+a file contains an operator that corresponds to a WordNet relation.  All 
+lines with the same <I>operator </I> value are stored in the file <B>wn_ </B><I>operator 
+</I><B>.pl </B>. <P>
+ The general format of a line in a prolog database file is as follows: 
+<P>
+  <blockquote><I>operator<B>(<I>field1<B>,<I>&nbsp;&nbsp;...&nbsp;&nbsp;<B>,<I>fieldn<B>). </B></I></B></I></B></I></B></I> <BR>
+  </blockquote>
+<P>
+ Each line contains the name of the 
+operator, followed by a left parenthesis, a comma-separated list of fields, 
+a right parenthesis, and a period.  Note there are no spaces, and each 
+line is terminated with a newline character.   
+<H3><A NAME="sect3" HREF="#toc3">Operators </A></H3>
+Each WordNet relation 
+is represented in a separate file by <I>operator </I> name.  Some operators are 
+reflexive (i.e. the "reverse" relation is implicit).  So, for example, if 
+<B>x </B> is a hypernym of <B>y </B>, <B>y </B> is necessarily a hyponym of <B>x </B>.  In the prolog 
+database, reflected pointers are usually implied for semantic relations. 
+<P>
+ Semantic relations are represented by a pair of <I>synset_id </I>s, in which 
+the first <I>synset_id </I> is generally the source of the relation and the second 
+is the target.  If two pairs <I>synset_id </I><B>, </B><I>w_num </I> are present, the operator 
+represents a lexical relation between word forms. <P>
+ <B>s(<I>synset_id<B>,<I>w_num<B>,'<I>word<B>',<I>ss_type<B>,<I>sense_number<B>,<I>tag_count<B>). 
+</B></I></B></I></B></I></B></I></B></I></B></I></B><BR>
+  <blockquote>A <B>s </B> operator is present for every word sense in WordNet.  In <B>wn_s.pl 
+</B>, <I>w_num </I> specifies the word number for <I>word </I> in the synset.  </blockquote>
+<P>
+ <B>g(<I>synset_id<B>,'(<I>gloss<B>)'). 
+</B></I></B></I></B><BR>
+  <blockquote>The <B>g </B> operator specifies the gloss for a synset.    </blockquote>
+<P>
+ <B>hyp(<I>synset_id<B>,<I>synset_id<B>). 
+</B></I></B></I></B><BR>
+  <blockquote>The <B>hyp </B> operator specifies that the second synset is a hypernym of 
+the first synset.  This relation holds for nouns and verbs.  The reflexive 
+operator, hyponym, implies that the first synset is a hyponym of the second 
+synset.  </blockquote>
+<P>
+ <B>ent(<I>synset_id<B>,<I>synset_id<B>). </B></I></B></I></B><BR>
+  <blockquote>The <B>ent </B> operator specifies that the 
+second synset is an entailment of first synset.  This relation only holds 
+for verbs.  </blockquote>
+<P>
+ <B>sim(<I>synset_id<B>,<I>synset_id<B>). </B></I></B></I></B><BR>
+  <blockquote>The <B>sim </B> operator specifies that 
+the second synset is similar in meaning to the first synset.  This means 
+that the second synset is a satellite the first synset, which is the cluster 
+head.  This relation only holds for adjective synsets contained in adjective 
+clusters.  </blockquote>
+<P>
+ <B>mm(<I>synset_id<B>,<I>synset_id<B>). </B></I></B></I></B><BR>
+  <blockquote>The <B>mm </B> operator specifies that the 
+second synset is a member meronym of the first synset.  This relation only 
+holds for nouns.  The reflexive operator, member holonym, can be implied. 
+ </blockquote>
+<P>
+ <B>ms(<I>synset_id<B>,<I>synset_id<B>). </B></I></B></I></B><BR>
+  <blockquote>The <B>ms </B> operator specifies that the second 
+synset is a substance meronym of the first synset.  This relation only 
+holds for nouns.  The reflexive operator, substance holonym, can be implied. 
+ </blockquote>
+<P>
+ <B>mp(<I>synset_id<B>,<I>synset_id<B>). </B></I></B></I></B><BR>
+  <blockquote>The <B>mp </B> operator specifies that the second 
+synset is a part meronym of the first synset.  This relation only holds 
+for nouns.  The reflexive operator, part holonym, can be implied.  </blockquote>
+<P>
+ <B>cs(<I>synset_id<B>,<I>synset_id<B>). 
+</B></I></B></I></B><BR>
+  <blockquote>The <B>cs </B> operator specifies that the second synset is a cause of the 
+first synset.  This relation only holds for verbs.  </blockquote>
+<P>
+ <B>vgp(<I>synset_id<B>,<I>synset_id<B>). 
+</B></I></B></I></B><BR>
+  <blockquote>The <B>vgp </B> operator specifies verb synsets that are similar in meaning 
+and should be grouped together when displayed in response to a grouped 
+synset search.  </blockquote>
+<P>
+ <B>at(<I>synset_id<B>,<I>synset_id<B>). </B></I></B></I></B><BR>
+  <blockquote>The <B>at </B> operator defines the 
+attribute relation between noun and adjective synset pairs in which the 
+adjective is a value of the noun. For each pair, both relations are listed 
+(ie. each <I>synset_id </I> is both a source and target).  </blockquote>
+<P>
+ <B>ant(<I>synset_id<B>,<I>w_num<B>,<I>synset_id<B>,<I>w_num<B>). 
+</B></I></B></I></B></I></B></I></B><BR>
+  <blockquote>The <B>ant </B> operator specifies antonymous <I>word </I>s.  This is a lexical relation 
+that holds for all syntactic categories.  For each antonymous pair, both 
+relations are listed (ie. each <I>synset_id,w_num </I> pair is both a source and 
+target word.)  </blockquote>
+<P>
+ <B>sa(<I>synset_id<B>,<I>w_num<B>,<I>synset_id<B>,<I>w_num<B>). </B></I></B></I></B></I></B></I></B><BR>
+  <blockquote>The <B>sa </B> operator 
+specifies that additional information about the first word can be obtained 
+by seeing the second word.  This operator is only defined for verbs and 
+adjectives.  There is no reflexive relation (ie. it cannot be inferred that 
+the additional information about the second word can be obtained from 
+the first word).  </blockquote>
+<P>
+ <B>ppl(<I>synset_id<B>,<I>w_num<B>,<I>synset_id<B>,<I>w_num<B>). </B></I></B></I></B></I></B></I></B><BR>
+  <blockquote>The <B>ppl </B> operator 
+specifies that the adjective first word is a participle of the verb second 
+word.  The reflexive operator can be implied.   </blockquote>
+<P>
+ <B>per(<I>synset_id<B>,<I>w_num<B>,<I>synset_id<B>,<I>w_num<B>). 
+</B></I></B></I></B></I></B></I></B><BR>
+  <blockquote>The <B>per </B> operator specifies two different relations based on the parts 
+of speech involved.  If the first word is in an adjective synset, that 
+word pertains to either the noun or adjective second word.  If the first 
+word is in an adverb synset, that word is derived from the adjective second 
+word.  </blockquote>
+<P>
+ <B>fr(<I>synset_id<B>,<I>f_num<B>,<I>w_num<B>). </B></I></B></I></B></I></B><BR>
+  <blockquote>The <B>fr </B> operator specifies a generic 
+sentence frame for one or all words in a synset.  The operator is defined 
+only for verbs.  </blockquote>
+ 
+<H3><A NAME="sect4" HREF="#toc4">Field Definitions </A></H3>
+A <I>synset_id </I> is a nine byte field in 
+which the first byte defines the syntactic category of the synset and 
+the remaining eight bytes are a <I>synset_offset </I>, as defined in  <B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+, 
+indicating the byte offset in the <B>data. </B><I>pos </I> file that corresponds to the 
+syntactic category. <P>
+ The syntactic category is encoded as:   <P>
+  <blockquote><B>1 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;NOUN <BR>
+ 
+<B>2 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;VERB <BR>
+ <B>3 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADJECTIVE <BR>
+ <B>4 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADVERB <BR>
+  </blockquote>
+<P>
+ <I>w_num </I>, if present, indicates which word 
+in the synset is being referred to.  Word numbers are assigned to the <I>word 
+</I> fields in a synset, from left to right, beginning with 1.  When used to 
+represent lexical WordNet relations <I>w_num </I> may be 0, indicating that the 
+relation holds for all words in the synset indicated by the preceding 
+<I>synset_id </I>.  See <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+ for a discussion of semantic and lexical 
+relations. <P>
+ <I>ss_type </I> is a one character code indicating the synset type: 
+<P>
+  <blockquote><B>n </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;NOUN <BR>
+ <B>v </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;VERB <BR>
+ <B>a </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADJECTIVE <BR>
+ <B>s </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADJECTIVE&nbsp;SATELLITE <BR>
+ <B>r </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADVERB <BR>
+  </blockquote>
+<P>
+ <I>sense_number 
+</I> specifies the sense number of the word, within the part of speech encoded 
+in the <I>synset_id </I>, in the WordNet database. <P>
+ <I>word </I> is the ASCII text of 
+the word as entered in the synset by the lexicographer, with spaces replaced 
+by underscore characters (<B>_ </B>).  The text of the word is case sensitive. 
+ An adjective <I>word </I> is immediately followed by a syntactic marker if one 
+was specified in the lexicographer file.  A syntactic marker is appended, 
+in parentheses, onto <I>word </I> without any intervening spaces.  See <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+ 
+for a list of the syntactic markers for adjectives. <P>
+ Each synset has a 
+<I>gloss </I> that may contain a definition, one or more example sentences, or 
+both.  Note that glosses are enclosed in single forward quotes and parentheses:&nbsp;&nbsp;<B>'(<I>gloss<B>)' 
+</B></I></B>. <P>
+ <I>f_num </I> specifies the generic sentence frame number for word <I>w_num </I> in 
+the synset indicated by <I>synset_id </I>.  Note that when <I>w_num </I> is <B>0 </B>, the frame 
+number applies to all words in the synset.  If non-zero, the frame applies 
+to that word in the synset. <P>
+ In WordNet, sense numbers are assigned as 
+described in  <B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+. <I>tag_count </I> is the number of times the sense was 
+tagged in the Semantic Concordances, and <B>0 </B> if it was not instantiated. 
+ 
+<H2><A NAME="sect5" HREF="#toc5">NOTES </A></H2>
+Since single forward quotes are used to enclose character strings, 
+single quote characters found in <I>word </I> and <I>gloss </I> fields are represented 
+as two adjacent single quote characters. <P>
+ The load time can be greatly 
+reduced by creating "object language" versions of the files, an option 
+that is supported by some implementations, such as Quintus Prolog.   
+<H2><A NAME="sect6" HREF="#toc6">ENVIRONMENT 
+VARIABLES (UNIX) </A></H2>
+
+<DL>
+
+<DT><B>WNHOME</B>  </DT>
+<DD>Base directory for WordNet.  Default is <B>/usr/local/WordNet-3.0 
+</B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect7" HREF="#toc7">REGISTRY (WINDOWS) </A></H2>
+
+<DL>
+
+<DT><B>HKEY_LOCAL_MACHINE\SOFTWARE\WordNet\3.0\WNHome</B>  </DT>
+<DD>Base directory 
+for WordNet.  Default is <B>C:\Program&nbsp;Files\WordNet\3.0 </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect8" HREF="#toc8">FILES </A></H2>
+All files are 
+in <B>WNHOME/prolog </B> on Unix platforms and <B>WNHome\prolog </B> on Windows platforms 
+
+<DL>
+
+<DT><B>wn_s.pl</B>  </DT>
+<DD>synset pointers </DD>
+
+<DT><B>wn_g.pl</B>  </DT>
+<DD>gloss pointers </DD>
+
+<DT><B>wn_hyp.pl</B>  </DT>
+<DD>hypernym pointers 
+</DD>
+
+<DT><B>wn_ent.pl</B>  </DT>
+<DD>entailment pointers </DD>
+
+<DT><B>wn_sim.pl</B>  </DT>
+<DD>similar pointers </DD>
+
+<DT><B>wn_mm.pl</B>  </DT>
+<DD>member 
+meronym pointers </DD>
+
+<DT><B>wn_ms.pl</B>  </DT>
+<DD>substance meronym pointers </DD>
+
+<DT><B>wn_mp.pl</B>  </DT>
+<DD>part meronym 
+pointers </DD>
+
+<DT><B>wn_cs.pl</B>  </DT>
+<DD>cause pointers </DD>
+
+<DT><B>wn_vgp.pl</B>  </DT>
+<DD>grouped verb pointers </DD>
+
+<DT><B>wn_at.pl</B> 
+ </DT>
+<DD>attribute pointers </DD>
+
+<DT><B>wn_ant.pl</B>  </DT>
+<DD>antonym pointers </DD>
+
+<DT><B>wn_sa.pl</B>  </DT>
+<DD>see also pointers 
+ </DD>
+
+<DT><B>wn_ppl.pl</B>  </DT>
+<DD>participle pointers </DD>
+
+<DT><B>wn_per.pl</B>  </DT>
+<DD>pertainym pointers </DD>
+
+<DT><B>wn_fr.pl</B>  </DT>
+<DD>frame 
+pointers </DD>
+</DL>
+ 
+<H2><A NAME="sect9" HREF="#toc9">SEE ALSO </A></H2>
+<B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+, <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+, <B><A HREF="wngroups.7WN.html">wngroups</B>(7WN)</A>
+, <B><A HREF="wnpkgs.7WN.html">wnpkgs</B>(7WN)</A>
+. 
+<P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">DESCRIPTION</A></LI>
+<UL>
+<LI><A NAME="toc2" HREF="#sect2">File Format</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">Operators</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">Field Definitions</A></LI>
+</UL>
+<LI><A NAME="toc5" HREF="#sect5">NOTES</A></LI>
+<LI><A NAME="toc6" HREF="#sect6">ENVIRONMENT VARIABLES (UNIX)</A></LI>
+<LI><A NAME="toc7" HREF="#sect7">REGISTRY (WINDOWS)</A></LI>
+<LI><A NAME="toc8" HREF="#sect8">FILES</A></LI>
+<LI><A NAME="toc9" HREF="#sect9">SEE ALSO</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/senseidx.5WN.html

@@ -0,0 +1,184 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>SENSEIDX(5WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+index.sense, sense.idx - WordNet's sense index  
+<H2><A NAME="sect1" HREF="#toc1">DESCRIPTION </A></H2>
+The WordNet 
+sense index provides an alternate method for accessing synsets and word 
+senses in the WordNet database.  It is useful to applications that retrieve 
+synsets or other information related to a specific sense in WordNet, rather 
+than all the senses of a word or collocation.  It can also be used with 
+tools like <B>grep </B> and Perl to find all senses of a word in one or more 
+parts of speech.  A specific WordNet sense, encoded as a <I>sense_key </I>, can 
+be used as an index into this file to obtain its WordNet sense number, 
+the database byte offset of the synset containing the sense, and the number 
+of times it has been tagged in the semantic concordance texts. <P>
+ Concatenating 
+the <I>lemma </I> and <I>lex_sense </I> fields of a semantically tagged word (represented 
+in a <B>&lt;wf&nbsp; </B>...&nbsp;<B>&gt; </B> attribute/value pair) in a semantic concordance file, using 
+<B>% </B> as the concatenation character, creates the <I>sense_key </I> for that sense, 
+which can in turn be used to search the sense index file. <P>
+ A <I>sense_key 
+</I> is the best way to represent a sense in semantic tagging or other systems 
+that refer to WordNet senses. <I>sense_key </I>s are independent of WordNet sense 
+numbers and <I>synset_offset </I>s, which vary between versions of the database. 
+Using the sense index and a <I>sense_key </I>, the corresponding synset (via 
+the <I>synset_offset </I>) and WordNet sense number can easily be obtained.  A 
+mapping from noun <I>sense_key </I>s in WordNet 1.6 to corresponding 2.0 <I>sense_key 
+</I>s is provided with version 2.0, and is described in <B><A HREF="sensemap.5WN.html">sensemap</B>(5WN)</A>
+. <P>
+ See 
+<B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+ for a thorough discussion of the WordNet database files.  
+<H3><A NAME="sect2" HREF="#toc2">File 
+Format </A></H3>
+The sense index file lists all of the senses in the WordNet database 
+with each line representing one sense.  The file is in alphabetical order, 
+fields are separated by one space, and each line is terminated with a 
+newline character. <P>
+ Each line is of the form: <P>
+  <blockquote><I>sense_key&nbsp;&nbsp;synset_offset&nbsp;&nbsp;sense_number&nbsp;&nbsp;tag_cnt 
+</I>  </blockquote>
+<P>
+ <I>sense_key </I> is an encoding of the word sense.  Programs can construct 
+a sense key in this format and use it as a binary search key into the 
+sense index file.   The format of a <I>sense_key </I> is described below. <P>
+ <I>synset_offset 
+</I> is the byte offset that the synset containing the sense is found at in 
+the database "data" file corresponding to the part of speech encoded in 
+the <I>sense_key </I>.  <I>synset_offset </I> is an 8 digit, zero-filled decimal integer, 
+and can be used with <B><A HREF="fseek.3.html">fseek</B>(3)</A>
+ to read a synset from the data file.  When 
+passed to the WordNet library function <B>read_synset() </B> along with the syntactic 
+category, a data structure containing the parsed synset is returned. <P>
+ <I>sense_number 
+</I> is a decimal integer indicating the sense number of the word, within 
+the part of speech encoded in <I>sense_key </I>, in the WordNet database.  See 
+<B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+ for information about how sense numbers are assigned. <P>
+ <I>tag_cnt 
+</I> represents the decimal number of times the sense is tagged in various 
+semantic concordance texts.  A <I>tag_cnt </I> of <B>0 </B> indicates that the sense 
+has not been semantically tagged.  
+<H3><A NAME="sect3" HREF="#toc3">Sense Key Encoding </A></H3>
+A <I>sense_key </I> is represented 
+as: <P>
+  <blockquote><I>lemma </I><B>% </B><I>lex_sense </I>  </blockquote>
+<P>
+ where <I>lex_sense </I> is encoded as: <P>
+  <blockquote><I>ss_type<B>:<I>lex_filenum<B>:<I>lex_id<B>:<I>head_word<B>:<I>head_id 
+</I></B></I></B></I></B></I></B></I>  </blockquote>
+<P>
+ <I>lemma </I> is the ASCII text of the word or collocation as found in the 
+WordNet database index file corresponding to <I>pos </I>. <I>lemma </I> is in lower case, 
+and collocations are formed by joining individual words with an underscore 
+(<B>_ </B>) character. <P>
+ <I>ss_type </I> is a one digit decimal integer representing the 
+synset type for the sense.  See <FONT SIZE=-1><B>Synset Type </B></FONT>
+  below for a listing of the 
+numbers corresponding to each synset type. <P>
+ <I>lex_filenum </I> is a two digit 
+decimal integer representing the name of the lexicographer file containing 
+the synset for the sense. See <B><A HREF="lexnames.5WN.html">lexnames</B>(5WN)</A>
+ for the list of lexicographer 
+file names and their corresponding numbers. <P>
+ <I>lex_id </I> is a two digit decimal 
+integer that, when appended onto <I>lemma </I>, uniquely identifies a sense within 
+a lexicographer file. <I>lex_id </I> numbers usually start with <B>00 </B>, and are incremented 
+as additional senses of the word are added to the same file, although 
+there is no requirement that the numbers be consecutive or begin with 
+<B>00 </B>.  Note that a value of <B>00 </B> is the default, and therefore is not present 
+in lexicographer files.  Only non-default <I>lex_id </I> values must be explicitly 
+assigned in lexicographer files.  See <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+ for information on the 
+format of lexicographer files. <P>
+ <I>head_word </I> is only present if the sense 
+is in an adjective satellite synset.  It is the lemma of the first word 
+of the satellite's head synset. <P>
+ <I>head_id </I> is a two digit decimal integer 
+that, when appended onto <I>head_word </I>, uniquely identifies the sense of 
+<I>head_word </I> within a lexicographer file, as described for <I>lex_id </I>.  There 
+is a value in this field only if <I>head_word </I> is present.  
+<H3><A NAME="sect4" HREF="#toc4">Synset Type </A></H3>
+The 
+synset type is encoded as follows: <P>
+  <blockquote><B>1 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;NOUN <BR>
+ <B>2 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;VERB <BR>
+ <B>3 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADJECTIVE <BR>
+ <B>4 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADVERB 
+<BR>
+ <B>5 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADJECTIVE SATELLITE <BR>
+  </blockquote>
+ 
+<H2><A NAME="sect5" HREF="#toc5">NOTES </A></H2>
+For non-satellite senses the <I>head_word 
+</I> and <I>head_id </I> fields have no values, however the field separator character 
+(<B>: </B>) is present.   
+<H2><A NAME="sect6" HREF="#toc6">ENVIRONMENT VARIABLES (UNIX) </A></H2>
+
+<DL>
+
+<DT><B>WNHOME</B>  </DT>
+<DD>Base directory 
+for WordNet.  Default is <B>/usr/local/WordNet-3.0 </B>. </DD>
+
+<DT><B>WNSEARCHDIR</B>  </DT>
+<DD>Directory in 
+which the WordNet database has been installed.   Default is <B>WNHOME/dict 
+</B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect7" HREF="#toc7">REGISTRY (WINDOWS) </A></H2>
+
+<DL>
+
+<DT><B>HKEY_LOCAL_MACHINE\SOFTWARE\WordNet\3.0\WNHome</B>  </DT>
+<DD>Base directory 
+for WordNet.  Default is <B>C:\Program&nbsp;Files\WordNet\3.0 </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect8" HREF="#toc8">FILES </A></H2>
+
+<DL>
+
+<DT><B>index.sense</B>  </DT>
+<DD>sense 
+index </DD>
+</DL>
+ 
+<H2><A NAME="sect9" HREF="#toc9">SEE ALSO </A></H2>
+<B><A HREF="binsrch.3WN.html">binsrch</B>(3WN)</A>
+, <B><A HREF="wnsearch.3WN.html">wnsearch</B>(3WN)</A>
+, <B><A HREF="lexnames.5WN.html">lexnames</B>(5WN)</A>
+, <B><A HREF="wnintro.5WN.html">wnintro</B>(5WN)</A>
+, 
+<B><A HREF="sensemap.5WN.html">sensemap</B>(5WN)</A>
+, <B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+, <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+. <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">DESCRIPTION</A></LI>
+<UL>
+<LI><A NAME="toc2" HREF="#sect2">File Format</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">Sense Key Encoding</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">Synset Type</A></LI>
+</UL>
+<LI><A NAME="toc5" HREF="#sect5">NOTES</A></LI>
+<LI><A NAME="toc6" HREF="#sect6">ENVIRONMENT VARIABLES (UNIX)</A></LI>
+<LI><A NAME="toc7" HREF="#sect7">REGISTRY (WINDOWS)</A></LI>
+<LI><A NAME="toc8" HREF="#sect8">FILES</A></LI>
+<LI><A NAME="toc9" HREF="#sect9">SEE ALSO</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/uniqbeg.7WN.html

@@ -0,0 +1,53 @@
+<!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>UNIQBEG(7WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+uniqbeg - unique beginners for noun hierarchies  
+<H2><A NAME="sect1" HREF="#toc1">DESCRIPTION </A></H2>
+All 
+of the WordNet noun synsets are organized into hierarchies, headed by 
+the unique beginner synset for <B>entity </B> in the file <B>noun.Tops </B>.  <P>
+  <blockquote>{ entity 
+(that which is perceived or known or inferred to have its own  <BR>
+ distinct 
+existence (living or nonliving)) } <BR>
+ <P>
+  </blockquote>
+ 
+<H2><A NAME="sect2" HREF="#toc2">NOTES </A></H2>
+The lexicographer files are 
+not included in the WordNet database package.  
+<H2><A NAME="sect3" HREF="#toc3">FILES </A></H2>
+
+<DL>
+
+<DT><B>noun.Tops</B>  </DT>
+<DD>unique beginners 
+for nouns </DD>
+</DL>
+ 
+<H2><A NAME="sect4" HREF="#toc4">SEE ALSO </A></H2>
+<B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+, <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+, <B><A HREF="wnintro.7WN.html">wnintro</B>(7WN)</A>
+, <B><A HREF="wngloss.7WN.html">wngloss</B>(7WN)</A>
+. 
+<P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">DESCRIPTION</A></LI>
+<LI><A NAME="toc2" HREF="#sect2">NOTES</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">FILES</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">SEE ALSO</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wn.1WN.html

@@ -0,0 +1,388 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WN(1WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+wn - command line interface to WordNet lexical database    
+<H2><A NAME="sect1" HREF="#toc1">SYNOPSIS 
+</A></H2>
+<B>wn </B> [ <I>searchstr </I> ] [ <B>-h </B>] [ <B>-g </B> ] [ <B>-a </B> ] [ <B>-l </B> ] [ <B>-o </B> ] [ <B>-s </B> ] [ <B>-n<I># </I></B> ] [ 
+<I>search_option </I>... ]  
+<H2><A NAME="sect2" HREF="#toc2">DESCRIPTION </A></H2>
+<B>wn() </B> provides a command line interface 
+to the WordNet database, allowing synsets and relations to be displayed 
+as formatted text.  For each word, different searches are provided, based 
+on syntactic category and pointer types.  Although only base forms of words 
+are usually stored in WordNet, users may search for inflected forms.  A 
+morphological process is applied to the search string to generate a form 
+that is present in WordNet. <P>
+ The command line interface is often useful 
+when writing scripts to extract information from the WordNet database. 
+ Post-processing of the output with various scripting tools can reformat 
+the results as desired.  
+<H2><A NAME="sect3" HREF="#toc3">OPTIONS </A></H2>
+
+<DL>
+
+<DT><B>-h</B>  </DT>
+<DD>Print help text before search results. 
+</DD>
+
+<DT><B>-g</B>  </DT>
+<DD>Display textual glosses associated with synsets. </DD>
+
+<DT><B>-a</B>  </DT>
+<DD>Display lexicographer 
+file information. </DD>
+
+<DT><B>-o</B>  </DT>
+<DD>Display synset offset of each synset. </DD>
+
+<DT><B>-s</B>  </DT>
+<DD>Display each 
+word's sense numbers in synsets. </DD>
+
+<DT><B>-l</B>  </DT>
+<DD>Display the WordNet copyright notice, 
+version number, and license. </DD>
+
+<DT><B>-n<I># </I></B>  </DT>
+<DD>Perform search on sense number <I># </I> only. 
+</DD>
+
+<DT><B>-over </B>  </DT>
+<DD>Display overview of all senses of <I>searchstr </I> in all syntactic categories. 
+ </DD>
+</DL>
+ 
+<H3><A NAME="sect4" HREF="#toc4">Search Options </A></H3>
+Note that the last letter of <I>search_option </I> generally 
+denotes the part of speech that the search applies to: <B>n </B> for nouns, <B>v 
+</B> for verbs, <B>a </B> for adjectives, and <B>r </B> for adverbs.  Multiple searches may 
+be done for <I>searchstr </I> with a single command by specifying all the appropriate 
+search options. <P>
+ 
+<DL>
+
+<DT><B>-syns </B>(<I>n </I> | <I>v </I> | <I>a </I> | <I>r </I>)   </DT>
+<DD>Display synonyms and immediate 
+hypernyms of synsets containing <I>searchstr </I>. Synsets are ordered by estimated 
+frequency of use.  For adjectives, if <I>searchstr </I> is in a head synset, the 
+cluster's satellite synsets are displayed in place of hypernyms.  If <I>searchstr 
+</I> is in a satellite synset, its head synset is also displayed. </DD>
+
+<DT><B>-simsv </B>  </DT>
+<DD>Display 
+verb synonyms and immediate hypernyms of synsets containing <I>searchstr 
+</I>.  Synsets are grouped by similarity of meaning. </DD>
+
+<DT><B>-ants </B>(<I>n </I> | <I>v </I> | <I>a </I> | <I>r </I>)  
+</DT>
+<DD>Display synsets containing antonyms of <I>searchstr </I>. For adjectives, if <I>searchstr 
+</I> is in a head synset, <I>searchstr </I> has a direct antonym. The head synset 
+for the direct antonym is displayed along with the direct antonym's satellite 
+synsets.  If <I>searchstr </I> is in a satellite synset, <I>searchstr </I> has an indirect 
+antonym via the head synset, which is displayed. </DD>
+
+<DT><B>-faml </B>(<I>n </I> | <I>v </I> | <I>a </I> | <I>r </I>) 
+ </DT>
+<DD>Display familiarity and polysemy information for <I>searchstr </I>. </DD>
+
+<DT><B>-hype </B>(<I>n </I> 
+| <I>v </I>)  </DT>
+<DD>Recursively display hypernym (superordinate) tree for <I>searchstr 
+</I> (<I>searchstr </I> <I>IS A KIND OF _____ </I> relation). </DD>
+
+<DT><B>-hypo </B>(<I>n </I> | <I>v </I>)  </DT>
+<DD>Display immediate 
+hyponyms (subordinates) for <I>searchstr </I> (<I>_____ IS A KIND OF </I> <I>searchstr 
+</I> relation). </DD>
+
+<DT><B>-tree </B>(<I>n </I> | <I>v </I>)  </DT>
+<DD>Display hyponym (subordinate) tree for <I>searchstr 
+</I>.  This is a recursive search that finds the hyponyms of each hyponym. </DD>
+
+<DT><B>-coor 
+</B>(<I>n </I> | <I>v </I>)  </DT>
+<DD>Display the coordinates (sisters) of <I>searchstr </I>.  This search 
+prints the immediate hypernym for each synset that contains <I>searchstr 
+</I> and the hypernym's immediate hyponyms. </DD>
+
+<DT><B>-deri </B>(<I>n </I> | <I>v </I>)  </DT>
+<DD>Display derivational 
+morphology links between noun and verb forms. </DD>
+
+<DT><B>-domn </B>(<I>n </I> | <I>v </I> | <I>a </I> | <I>r </I>)  </DT>
+<DD>Display 
+domain that <I>searchstr </I> has been classified in. </DD>
+
+<DT><B>-domt </B>(<I>n </I> | <I>v </I> | <I>a </I> | <I>r </I>)  </DT>
+<DD>Display 
+all terms classified as members of the <I>searchstr </I>'s domain. </DD>
+
+<DT><B>-subsn</B>  </DT>
+<DD>Display 
+substance meronyms of <I>searchstr </I> (<I>HAS SUBSTANCE </I> relation). </DD>
+
+<DT><B>-partn</B>  </DT>
+<DD>Display 
+part meronyms of <I>searchstr </I> (<I>HAS PART </I> relation). </DD>
+
+<DT><B>-membn</B>  </DT>
+<DD>Display member 
+meronyms of <I>searchstr </I> (<I>HAS MEMBER </I> relation). </DD>
+
+<DT><B>-meron</B>  </DT>
+<DD>Display all meronyms 
+of <I>searchstr </I> (<I>HAS PART, HAS MEMBER, HAS SUBSTANCE </I> relations). </DD>
+
+<DT><B>-hmern</B>  
+</DT>
+<DD>Display meronyms for <I>searchstr </I> tree.  This is a recursive search that 
+prints all the meronyms of <I>searchstr </I> and all of its hypernyms. </DD>
+
+<DT><B>-sprtn</B>  
+</DT>
+<DD>Display <I>part of </I> holonyms of <I>searchstr </I> (<I>PART OF </I> relation). </DD>
+
+<DT><B>-smemn</B>  </DT>
+<DD>Display 
+<I>member of </I> holonyms of <I>searchstr </I> (<I>MEMBER OF </I> relation). </DD>
+
+<DT><B>-ssubn</B>  </DT>
+<DD>Display 
+<I>substance of </I> holonyms of <I>searchstr </I> (<I>SUBSTANCE OF </I> relation). </DD>
+
+<DT><B>-holon</B>  </DT>
+<DD>Display 
+all holonyms of <I>searchstr </I> (<I>PART OF, MEMBER OF, SUBSTANCE OF </I> relations). 
+</DD>
+
+<DT><B>-hholn</B>  </DT>
+<DD>Display holonyms for <I>searchstr </I> tree.  This is a recursive search 
+that prints all the holonyms of <I>searchstr </I> and all of each holonym's holonyms. 
+</DD>
+
+<DT><B>-entav</B>  </DT>
+<DD>Display entailment relations of <I>searchstr </I>. </DD>
+
+<DT><B>-framv</B>  </DT>
+<DD>Display applicable 
+verb sentence frames for <I>searchstr </I>.  </DD>
+
+<DT><B>-causv</B>  </DT>
+<DD>Display <I>cause to </I> relations 
+of <I>searchstr </I>. </DD>
+
+<DT><B> -pert </B>(<I>a </I> | <I>r </I>)  </DT>
+<DD>Display pertainyms of <I>searchstr </I>. </DD>
+
+<DT><B> -attr </B>(<I>n 
+</I> | <I>a </I>)  </DT>
+<DD>Display adjective values for noun attribute, or noun attributes 
+of adjective values. </DD>
+
+<DT><B>-grep </B>(<I>n </I> | <I>v </I> | <I>a </I> | <I>r </I>)  </DT>
+<DD>List compound words containing 
+<I>searchstr </I> as a substring. </DD>
+</DL>
+ 
+<H2><A NAME="sect5" HREF="#toc5">SEARCH RESULTS </A></H2>
+The results of a search are 
+written to the standard output.  For each search, the output consists a 
+one line description of the search, followed by the search results. <P>
+ All 
+searches other than <B>-over </B> list all senses matching the search results 
+in the following general format.  Items enclosed in italicized square brackets 
+(<I>[&nbsp;...&nbsp;] </I>) may not be present. <P>
+  <blockquote>One line listing the number of senses matching 
+the search request. <P>
+ Each sense matching the search requested displayed 
+as follows: <P>
+ <tt> </tt>&nbsp;<tt> </tt>&nbsp;<B>Sense <I>n </I></B> <BR>
+ <tt> </tt>&nbsp;<tt> </tt>&nbsp;<I>[<B>{<I>synset_offset<B>}<I>] [<B>&lt;<I>lex_filename<B>&gt;<I>]&nbsp;&nbsp;word1[<B>#<I>sense_number][,&nbsp;&nbsp;word2...] 
+</I></B></I></B></I></B></I></B></I></B></I> <BR>
+ <P>
+ Where <I>n </I> is the sense number of the search word, <I>synset_offset </I> is 
+the byte offset of the synset in the <B>data.<I>pos </I></B> file corresponding to the 
+syntactic category, <I>lex_filename </I> is the name of the lexicographer file 
+that the synset comes from, <I>word1 </I> is the first word in the synset (note 
+that this is not necessarily the search word) and <I>sense_number </I> is the 
+WordNet sense number assigned to the preceding word. <I>synset_offset, lex_filename 
+</I>, and <I>sense_number </I> are generated when the <B>-o, -a, </B> and <B>-s </B> options, respectively, 
+are specified. <P>
+ The synsets matching the search requested are printed below 
+each sense's synset output described above.  Each line of output is preceded 
+by a marker (usually <B>=&gt; </B>), then a synset, formatted as described above. 
+ If a search traverses more one level of the tree, then successive lines 
+are indented by spaces corresponding to its level in the hierarchy.  When 
+the <B>-g </B> option is specified, synset glosses are displayed in parentheses 
+at the end of each synset.  Each synset is printed on one line. <P>
+ Senses 
+are generally ordered from most to least frequently used, with the most 
+common sense numbered <B>1 </B>.  Frequency of use is determined by the number 
+of times a sense is tagged in the various semantic concordance texts.  
+Senses that are not semantically tagged follow the ordered senses.  Note 
+that this ordering is only an estimate based on usage in a small corpus. 
+<P>
+ Verb senses can be grouped by similarity of meaning, rather than ordered 
+by frequency of use.  The <B>-simsv </B> search prints all senses that are close 
+in meaning together, with a line of dashes indicating the end of a group. 
+ See <B><A HREF="wngroups.7WN.html">wngroups</B>(7WN)</A>
+ for a discussion of how senses are grouped. <P>
+ The <B>-over 
+</B> search displays an overview of all the senses of the search word in all 
+syntactic categories.  The results of this search are similar to the <B>-syns 
+</B> search, however no additional (ex. hypernym) synsets are displayed, and 
+synset glosses are always printed.  The senses are grouped by syntactic 
+category, and each synset is annotated as described above with <I>synset_offset 
+</I>, <I>lex_filename </I>, and <I>sense_number </I> as dictated by the <B>-o, -a, </B> and <B>-s </B> options. 
+ The overview search also indicates how many of the senses in each syntactic 
+category are represented in the tagged texts.  This is a way for the user 
+to determine whether a sense's sense number is based on semantic tagging 
+data, or was arbitrarily assigned.   For each sense that has appeared in 
+such texts, the number of semantic tags to that sense are indicated in 
+parentheses after the sense number. <P>
+ If a search cannot be performed on 
+some senses of <I>searchstr </I>, the search results are headed by a string of 
+the form: <tt> </tt>&nbsp;<tt> </tt>&nbsp;X of Y senses of <I>searchstr </I> <BR>
+ <P>
+ The output of the <B>-deri </B> search 
+shows word forms that are morphologically related to <B>searchstr </B>. Each word 
+form pointed to from <I>searchstr </I> is displayed, preceded by <B>RELATED TO-&gt; </B> 
+and the syntactic category of the link, followed, on the next line, by 
+its synset.  Printed after the word form is <B># </B><I>n </I> where <I>n </I> indicates the 
+WordNet sense number of the term pointed to. <P>
+ The <B>-domn </B> and <B>-domt </B> searches 
+show the domain that a synset has been classified in and, conversely, 
+all of the terms that have been assigned to a specific domain.  A domain 
+is either a <B>TOPIC, </B> <B>REGION </B> or <B>USAGE, </B> as reflected in the specific pointer 
+character stored in the database, and displayed in the output.  A <B>-domn 
+</B> search on a term shows the domain, if any, that each synset containing 
+<I>searchstr </I> has been classified in.  The output display shows the domain 
+type (<B>TOPIC, </B> <B>REGION </B> or <B>USAGE </B>), followed by the syntactic category of 
+the domain synset and the terms in the synset.  Each term is followed by 
+<B># </B><I>n </I> where <I>n </I> indicates the WordNet sense number of the term.  The converse 
+search, <B>-domt </B>, shows all of the synsets that have been placed into the 
+domain <I>searchstr </I>, with analogous markers.  <P>
+ When <B>-framv </B> is specified, 
+sample illustrative sentences and generic sentence frames are displayed. 
+ If a sample sentence is found, the base form of <I>search </I> is substituted 
+into the sentence, and it is printed below the synset, preceded with the 
+<B>EX: </B> marker.  When no sample sentences are found, the generic sentence 
+frames are displayed.  Sentence frames that are acceptable for all words 
+in a synset are preceded by the marker <B>*&gt; </B>.  If a frame is acceptable for 
+the search word only, it is preceded by the marker <B>=&gt; </B>. <P>
+ Search results 
+for adjectives are slightly different from those for other parts of speech. 
+ When an adjective is printed, its direct antonym, if it has one, is also 
+printed in parentheses.  When <I>searchstr </I> is in a head synset, all of the 
+head synset's satellites are also displayed.  The position of an adjective 
+in relation to the noun may be restricted to the <I>prenominal </I>, <I>postnominal 
+</I> or <I>predicative </I> position.  Where present, these restrictions are noted 
+in parentheses. <P>
+ When an adjective is a participle of a verb, the output 
+indicates the verb and displays its synset. <P>
+ When an adverb is derived 
+from an adjective, the specific adjectival sense on which it is based 
+is indicated. <P>
+ The morphological transformations performed by the search 
+code may result in more than one word to search for.  WordNet automatically 
+performs the requested search on all of the strings and returns the results 
+grouped by word.  For example, the verb <B>saw </B> is both the present tense 
+of <B>saw </B> and the past tense of <B>see </B>.  When passed <I>searchstr </I> <B>saw </B>, WordNet 
+performs the desired search first on <B>saw </B> and next on <B>see </B>, returning 
+the list of <B>saw </B> senses and search results, followed by those for <B>see 
+</B>.  </blockquote>
+ 
+<H2><A NAME="sect6" HREF="#toc6">EXIT STATUS </A></H2>
+<B>wn() </B> normally exits with the number of senses displayed. 
+ If <I>searchword </I> is not found in WordNet, it exits with <B>0 </B>. <P>
+ If the WordNet 
+database cannot be opened, an error messages is displayed and <B>wn() </B> exits 
+with <B>-1 </B>.  
+<H2><A NAME="sect7" HREF="#toc7">ENVIRONMENT VARIABLES (UNIX) </A></H2>
+
+<DL>
+
+<DT><B>WNHOME</B>  </DT>
+<DD>Base directory for WordNet. 
+ Default is <B>/usr/local/WordNet-3.0 </B>. </DD>
+
+<DT><B>WNSEARCHDIR</B>  </DT>
+<DD>Directory in which the 
+WordNet database has been installed.   Default is <B>WNHOME/dict </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect8" HREF="#toc8">REGISTRY 
+(WINDOWS) </A></H2>
+
+<DL>
+
+<DT><B>HKEY_LOCAL_MACHINE\SOFTWARE\WordNet\3.0\WNHome</B>  </DT>
+<DD>Base directory for 
+WordNet.  Default is <B>C:\Program&nbsp;Files\WordNet\3.0 </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect9" HREF="#toc9">FILES </A></H2>
+
+<DL>
+
+<DT><B>index.<I>pos </I></B>  </DT>
+<DD>database 
+index files </DD>
+
+<DT><B>data.<I>pos </I></B>  </DT>
+<DD>database data files </DD>
+
+<DT><B>*.vrb</B>  </DT>
+<DD>files of sentences illustrating 
+the use of verbs </DD>
+
+<DT><B><I>pos </I>.exc</B>  </DT>
+<DD>morphology exception lists </DD>
+</DL>
+ 
+<H2><A NAME="sect10" HREF="#toc10">SEE ALSO </A></H2>
+<B><A HREF="wnintro.1WN.html">wnintro</B>(1WN)</A>
+, 
+<B><A HREF="wnb.1WN.html">wnb</B>(1WN)</A>
+, <B><A HREF="wnintro.3WN.html">wnintro</B>(3WN)</A>
+, <B><A HREF="lexnames.5WN.html">lexnames</B>(5WN)</A>
+, <B><A HREF="senseidx.5WN.html">senseidx</B>(5WN)</A>
+ <B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+,<B></B> <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+, 
+<B><A HREF="morphy.7WN.html">morphy</B>(7WN)</A>
+, <B><A HREF="wngloss.7WN.html">wngloss</B>(7WN)</A>
+, <B><A HREF="wngroups.7WN.html">wngroups</B>(7WN)</A>
+.  
+<H2><A NAME="sect11" HREF="#toc11">BUGS </A></H2>
+Please report bugs to wordnet@princeton.edu. 
+<P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">SYNOPSIS</A></LI>
+<LI><A NAME="toc2" HREF="#sect2">DESCRIPTION</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">OPTIONS</A></LI>
+<UL>
+<LI><A NAME="toc4" HREF="#sect4">Search Options</A></LI>
+</UL>
+<LI><A NAME="toc5" HREF="#sect5">SEARCH RESULTS</A></LI>
+<LI><A NAME="toc6" HREF="#sect6">EXIT STATUS</A></LI>
+<LI><A NAME="toc7" HREF="#sect7">ENVIRONMENT VARIABLES (UNIX)</A></LI>
+<LI><A NAME="toc8" HREF="#sect8">REGISTRY (WINDOWS)</A></LI>
+<LI><A NAME="toc9" HREF="#sect9">FILES</A></LI>
+<LI><A NAME="toc10" HREF="#sect10">SEE ALSO</A></LI>
+<LI><A NAME="toc11" HREF="#sect11">BUGS</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wnb.1WN.html

@@ -0,0 +1,524 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WNB(1WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+wnb - WordNet window-based browser interface   
+<H2><A NAME="sect1" HREF="#toc1">SYNOPSIS </A></H2>
+<P>
+<B>wnb </B>  
+<H2><A NAME="sect2" HREF="#toc2">DESCRIPTION 
+</A></H2>
+<B>wnb() </B> provides a window-based interface for browsing the WordNet database, 
+allowing synsets and relations to be displayed as formatted text.  For 
+each search word, different searches are available based on syntactic 
+category and information available in the database.   <P>
+ <B>wnb </B> is written 
+in Tcl/Tk, which is available for Unix and Windows platforms.  This allows 
+the same code to work on all supported WordNet platforms without modification. 
+ 
+<H2><A NAME="sect3" HREF="#toc3">WNB WINDOWS </A></H2>
+<B>wnb() </B> was developed with the philosophy that only those 
+searches and buttons that are applicable at the current time are displayed. 
+ As a result, the appearance of the interface changes as it is used.  Use 
+the standard windowing system mouse functions to open and close the WordNet 
+Browser Window, move the window, and change its size. <P>
+ The WordNet Browser 
+Window contains the following areas, from top to bottom: 
+<DL>
+
+<DT>Menubar  </DT>
+<DD>A menubar 
+runs along the top of the browser window with pulldown menus and button 
+entitled <B>File </B>, <B>History </B>, <B>Options </B>, and <B>Help </B>. </DD>
+
+<DT>Search Word Entry   </DT>
+<DD>Below 
+the Menubar is a line for entering the search word.  A search word can 
+be a single word, hyphenated string, or a collocation.  Case is ignored. 
+ Although only uninflected forms of words are usually stored in WordNet, 
+users may search for inflected forms.  WordNet's morphological processor 
+finds the base form automatically. </DD>
+
+<DT>Search Selection  </DT>
+<DD>Below the Search Word 
+Entry line is an area for selecting the search type and senses to search. 
+ Until a search word is entered this area is blank.  After a search word 
+is entered, buttons appear corresponding to each syntactic category (<B>Noun 
+</B>, <B>Verb </B>, <B>Adjective </B>, <B>Adverb </B>) in which the search string is defined in 
+WordNet.   </DD>
+</DL>
+<P>
+ At the right edge of the Search Selection line is a box for 
+entering sense numbers.  When this box is empty, search results for all 
+senses of the search word that match the search type are displayed.  The 
+search may be restricted to one or more specific senses by entering a 
+comma or space separated list of sense numbers in the <B>Senses </B> box.  These 
+sense numbers remain in effect until either the user changes or deletes 
+them, or a new search word is entered. 
+<DL>
+
+<DT>Results Window  </DT>
+<DD>Most of the browser 
+window consists of a large text buffer for displaying the results of WordNet 
+searches.  Horizontal and vertical scroll bars are present for scrolling 
+through the output. </DD>
+
+<DT>Status Line   </DT>
+<DD>A status line is at the bottom of the 
+browser window. When search results are displayed in the Results Window, 
+this status line reflects the type of search selected.  When there is no 
+search word entered, your are prompted to <B>"Enter search word and press 
+return." </B>  If the search word entered is not in WordNet, the message <B>"Sorry, 
+no matches found." </B> is displayed. </DD>
+</DL>
+ 
+<H2><A NAME="sect4" HREF="#toc4">SEARCHING THE DATABASE </A></H2>
+The WordNet browser 
+navigates through WordNet in two steps.  First a search word is entered 
+and an overview of all the senses of the word in all syntactic categories 
+is displayed in the Results Window.   The senses are grouped by syntactic 
+category, and each synset is annotated as described above with <I>synset_offset 
+</I>, <I>lex_filename </I>, and <I>sense_number </I> as dictated by the advanced search 
+options set. The overview search also indicates how many of the senses 
+in each syntactic category are represented in the tagged texts.  This is 
+a way for the user to determine whether a sense's sense number is based 
+on semantic tagging data, or was arbitrarily assigned.  For each sense 
+that has appeared in such texts, the number of semantic tags to that sense 
+are indicated in parentheses after the sense number. <P>
+ Then, within a syntactic 
+category, a specific search is selected.  The desired search is performed 
+and the search results are displayed in the Results Window.  Additional 
+searches on the same word can be performed, or a new search word can be 
+entered. <P>
+ To enter a search word, click the mouse in the horizontal box 
+labeled <B>Search Word </B>, type a single word, hyphenated string, or collocation 
+and press <FONT SIZE=-1><B>RETURN. </B></FONT>
+  <P>
+ <B>wnb() </B> responds by making a set of Part of Speech 
+buttons appear in the Search Selection line.  Each button corresponds to 
+a syntactic category in which the search string is defined in WordNet. 
+ At the same time, an Overview of the synsets for all senses of the search 
+word is displayed in the Results Window.  The Overview includes the gloss 
+for each synset and also indicates which of the senses have appeared in 
+the semantically tagged texts.  For each sense that has appeared in such 
+texts, the number of semantic tags to that sense are indicated in parentheses 
+after the sense number. <P>
+ The pulldown menus in the Search Selection line 
+list all of the WordNet searches that can be performed for the search 
+word in that part of speech.  To select a search, highlight it by dragging 
+the mouse to it, and release the mouse while it is highlighted.  Drag the 
+mouse outside of the pulldown list and release to hide the menu without 
+making a selection.  Dragging the mouse across the Part of Speech buttons 
+displays the available searches for each syntactic category. <P>
+ To restrict 
+a search to one or more senses within a syntactic category, enter a comma 
+or space separated list of sense numbers in the <B>Senses </B> box before selecting 
+a search. <P>
+ After a search is selected, <B>wnb() </B> performs the search on the 
+WordNet database and displays the formatted results in the Results Window. 
+ Whenever search results are displayed, a button entitled <B>Redisplay Overview 
+</B> is present at the right edge of the Search Word Entry line.  Clicking 
+on this button redisplays the Overview of all synsets for the search word 
+in the Results Window.  
+<H3><A NAME="sect5" HREF="#toc5">Changing the Search Word </A></H3>
+A new search word can 
+be entered at any time by moving to the Search Word Entry box, if necessary 
+highlighting it by clicking, erasing the old string, typing a new one 
+and pressing <FONT SIZE=-1><B>RETURN. </B></FONT>
+  The <B>Senses </B> box is cleared if necessary, the Part 
+of Speech buttons applicable to the new search word appear, and the Overview 
+for the new search word is displayed.   <P>
+ The middle mouse button can also 
+be used to select a new search word by placing the mouse over any word 
+in the Results Window and clicking.  The selected word will replace the 
+text in the Search Word Entry box, and the overview for that word will 
+automatically be displayed. <P>
+ To select a new search string collocation 
+from text in the Results Window, highlight the text with the mouse and 
+press <FONT SIZE=-1><B>CONTROL-S. </B></FONT>
+  <P>
+  
+<H3><A NAME="sect6" HREF="#toc6">Interrupting a Search </A></H3>
+When a search is in progress 
+the message <B>"Searching...(press escape to abort)" </B> is displayed in the Status 
+Line.  Note that most searches return very quickly, so this message isn't 
+noticeable.  As indicated, pressing the <FONT SIZE=-1><B>ESCAPE </B></FONT>
+  key will interrupt the 
+search.  The results of the search obtained before the time the search 
+was interrupted are displayed in the Results Window.  
+<H2><A NAME="sect7" HREF="#toc7">MENUS </A></H2>
+ 
+<H3><A NAME="sect8" HREF="#toc8">File Menu 
+</A></H3>
+ <blockquote>
+<DL>
+
+<DT>Find keywords by substring </DT>
+<DD>Display a popup window for specifying a search 
+of WordNet for words or collocations that contain a specific substring. 
+ If a search word is currently entered in the <B>Search Word </B> box, it is 
+used as the substring to search for by default.  The Substring Search Window 
+contains a box for entering a substring, a pulldown menu to its right 
+for specifying the part of speech to search, a large area for displaying 
+the search results, and action buttons at the bottom entitled <B>Search </B>, 
+<B>Save </B>, <B>Print </B> <B>Dismiss </B>.  </DD>
+</DL>
+<P>
+ Once a substring is entered and a part of speech 
+selected, clicking on the <B>Search </B> button causes a search to be done for 
+all words and collocations in WordNet, in that syntactic category, that 
+contain the substring according to the following criteria: <P>
+ 1. The substring 
+can appear at the beginning or end of a word, hyphenated string o collocation. 
+<P>
+ 2. The substring can appear in the middle of a hyphenated string or collocation, 
+but only delimited on both sides by spaces or hyphens. <P>
+ The search results 
+are displayed in the large buffer.  Clicking on an item from the search 
+results list causes <B>wnb() </B> to automatically enter that word in the <B>Search 
+Word </B> box of the WordNet Browser Window and perform the Overview search. 
+<P>
+ Clicking the <B>Save </B> button generates a popup dialog for specifying a filename 
+to save the substring search results to.  Clicking the <B>Print </B> button generates 
+a popup dialog in which a print command can be specified. <P>
+ Selecting <B>Dismiss 
+</B> closes the Substring Search Window. 
+<DL>
+
+<DT>Save current display </DT>
+<DD>Display a popup 
+dialog for specifying a filename to save the current Results Window contents 
+to. </DD>
+
+<DT>Print current display </DT>
+<DD>Display a popup dialog in which to specify a 
+print command to which the current Results Window contents can be piped. 
+Note - this option does not exist in the Windows version. </DD>
+
+<DT>Clear current 
+display </DT>
+<DD>Clear the <B>Search Word </B> and <B>Senses </B> boxes, and Results Window. </DD>
+
+<DT>Exit 
+</DT>
+<DD>Does what you would expect. </DD>
+</DL>
+ </blockquote>
+ 
+<H3><A NAME="sect9" HREF="#toc9">History </A></H3>
+This pulldown menu contains a list 
+of the last searches performed. Selecting an item from this list performs 
+that search again.  The maximum number of searches stored in the list can 
+be adjusted from the <B>Options </B> menu.  The default is 10.  
+<H3><A NAME="sect10" HREF="#toc10">Options </A></H3>
+ <blockquote>
+<DL>
+
+<DT>Show help 
+with each search </DT>
+<DD>When this checkbox is selected search results are preceded 
+by some explanatory text about the type of search selected. This is off 
+by default. </DD>
+
+<DT>Show descriptive gloss </DT>
+<DD>When this checkbox is selected, synset 
+glosses are displayed in all search results.  This is set by default.  Note 
+that glosses are always displayed in the Overview. </DD>
+
+<DT>Wrap Lines </DT>
+<DD>When this 
+checkbox is selected, lines in the Results Window that are wider than 
+the window are automatically wrapped.  This is set by default.  If not selected, 
+a horizontal scroll bar is present if any lines are longer than the width 
+of the window. </DD>
+
+<DT>Set advanced search options... </DT>
+<DD>Selecting this item displays 
+a popup window for setting the following search options:  <B>Lexical file 
+information; Synset location in database file; Sense number </B>.  Choices 
+for each are: </DD>
+</DL>
+<P>
+ <tt> </tt>&nbsp;<tt> </tt>&nbsp;<B>Don't show </B> (default) <BR>
+ <tt> </tt>&nbsp;<tt> </tt>&nbsp;<B>Show with searches </B> <BR>
+ <tt> </tt>&nbsp;<tt> </tt>&nbsp;<B>Show with searches 
+and overview </B> <BR>
+ <P>
+ When lexical file information is shown, the name of the 
+lexicographer file is printed before each synset, enclosed in angle brackets 
+(<B>&lt;&nbsp;&nbsp;<I>...<B>&nbsp;&nbsp;&gt; </B></I></B>).  When both lexical file information and synset location information 
+are displayed, the synset location information appears first.  If within 
+one lexicographer file more than one sense of a word is entered, an integer 
+<I>lex_id </I> is appended onto all but one of the word's instances to uniquely 
+identify it.  In each synset, each word having a non-zero <I>lex_id </I> is printed 
+with the <I>lex_id </I> value printed immediately following the word.  If both 
+lexicographer information and sense numbers are displayed, <I>lex_id </I>s, if 
+present, precede sense numbers. <P>
+ When synset location is shown, the byte 
+offset of the synset in the database "data" file corresponding to the 
+syntactic category of the synset is printed before each synset, enclosed 
+in curly braces (<B>{&nbsp;&nbsp;<I>...<B>&nbsp;&nbsp;} </B></I></B>).  When both lexical file information and synset 
+location information are displayed, the synset location information appears 
+first. <P>
+ When sense numbers are shown, the sense number of each word in 
+each synset is printed immediately after the word, and is preceded by 
+a number sign (<B># </B>). 
+<DL>
+
+<DT>Set maximum history length... </DT>
+<DD>Display a popup dialog in 
+which the maximum number of previous searches to be kept on the History 
+list can be set. </DD>
+
+<DT>Set font...&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </DT>
+<DD>Display a popup window for setting 
+the font (typeface) and font size to use for the Results Window.  Choices 
+for typeface are: <B>Courier </B>, <B>Helvetica </B>, and <B>Times </B> (default).  Font size 
+can be <B>small </B>, <B>medium </B> (default), or <B>large </B>. </DD>
+
+<DT>Save current options as default 
+</DT>
+<DD>Save the currently set options.  Next time the browser is started, these 
+options will be used as the user defaults. </DD>
+</DL>
+ </blockquote>
+ 
+<H3><A NAME="sect11" HREF="#toc11">Help </A></H3>
+ <blockquote>
+<DL>
+
+<DT>Help on using the WordNet 
+browser </DT>
+<DD>Display this manual page. </DD>
+
+<DT>Help on WordNet terminology </DT>
+<DD>Display the 
+ <B><A HREF="wngloss.7WN.html">wngloss</B>(7WN)</A>
+ manual page. </DD>
+
+<DT>Display the WordNet license </DT>
+<DD>Display the WordNet 
+copyright notice and license agreement. </DD>
+
+<DT>About the WordNet browser </DT>
+<DD>Information 
+about this application. </DD>
+</DL>
+ </blockquote>
+ 
+<H2><A NAME="sect12" HREF="#toc12">SHORCUTS </A></H2>
+Clicking on any word in the Results 
+Window while holding down the  <FONT SIZE=-1><B>SHIFT </B></FONT>
+  key on the keyboard causes the 
+browser to replace <B>Search Word </B> with the word and display its Overview 
+and available searches. Clicking on any word in the Results Window with 
+the middle mouse button does the same thing. <P>
+ Pressing the <FONT SIZE=-1><B>CONTROL-S </B></FONT>
+  keys 
+causes the browser to do as above on the text that is currently highlighted. 
+ Under Unix, this will work even if the highlighted text is in another 
+window.  This works on hyphenated strings and collocations, as well as 
+individual words. <P>
+ Pressing the <FONT SIZE=-1><B>CONTROL-G </B></FONT>
+  keys displays the Substring 
+Search Window. <P>
+  
+<H2><A NAME="sect13" HREF="#toc13">SEARCH RESULTS </A></H2>
+The results of a search of the WordNet 
+database are displayed in the Results Window.  Horizontal and vertical 
+scroll bars are present for scrolling through the search results. <P>
+ All 
+searches other than the Overview list all senses matching the search results 
+in the following general format.  Items enclosed in italicized square brackets 
+(<I>[&nbsp;...&nbsp;] </I>) may not be present. <P>
+ If a search cannot be performed on some senses 
+of <I>searchstr </I>, the search results are headed by a string of the form: 
+<tt> </tt>&nbsp;<tt> </tt>&nbsp;X of Y senses of <I>searchstr </I> <BR>
+ <P>
+  <blockquote>One line listing the number of senses matching 
+the search selected. <P>
+ Each sense matching the search selected displayed 
+as follows: <P>
+ <tt> </tt>&nbsp;<tt> </tt>&nbsp;<B>Sense <I>n </I></B> <BR>
+ <tt> </tt>&nbsp;<tt> </tt>&nbsp;<I>[<B>{<I>synset_offset<B>}<I>] [<B>&lt;<I>lex_filename<B>&gt;<I>]&nbsp;&nbsp;word1[<B>#<I>sense_number][,&nbsp;&nbsp;word2...] 
+</I></B></I></B></I></B></I></B></I></B></I> <BR>
+ <P>
+ Where <I>n </I> is the sense number of the search word, <I>synset_offset </I> is 
+the byte offset of the synset in the <B>data.<I>pos </I></B> file corresponding to the 
+syntactic category, <I>lex_filename </I> is the name of the lexicographer file 
+that the synset comes from, <I>word1 </I> is the first word in the synset (note 
+that this is not necessarily the search word) and <I>sense_number </I> is the 
+WordNet sense number assigned to the preceding word. <I>synset_offset </I>, <I>lex_filename 
+</I>, and <I>sense_number </I> are generated if the appropriate Options are specified. 
+<P>
+ The synsets matching the search selected are printed below each sense's 
+synset output described above.  Each line of output is preceded by a marker 
+(usually <B>=&gt; </B>), then a synset, formatted as described above.  If a search 
+traverses more one level of the tree, then successive lines are indented 
+by spaces corresponding to its level in the hierarchy.  Glosses are displayed 
+in parentheses at the end of each synset if the appropriate Option is 
+set.  Each synset is printed on one line. <P>
+ Senses are ordered from most 
+to least frequently used, with the most common sense numbered <B>1 </B>.  Frequency 
+of use is determined by the number of times a sense is tagged in the various 
+semantic concordance texts.  Senses that are not semantically tagged follow 
+the ordered senses. Note that this ordering is only an estimate based on 
+usage in a small corpus. <P>
+ Verb senses can be grouped by similarity of meaning, 
+rather than ordered by frequency of use.  When the <B>"Synonyms, grouped by 
+similarity" </B> search is selected, senses that are close in meaning are 
+printed together, with a line of dashes indicating the end of a group. 
+ See <B><A HREF="wngroups.7WN.html">wngroups</B>(7WN)</A>
+ for a discussion how senses are grouped. <P>
+ The output 
+of the <B>"Derivationally Related Forms" </B>  search shows word forms that are 
+morphologically related to <B>searchstr </B>. Each word form pointed to from <I>searchstr 
+</I> is displayed, preceded by <B>RELATED TO-&gt; </B> and the syntactic category of the 
+link, followed, on the next line, by its synset.  Printed after the word 
+form is <B># </B><I>n </I> where <I>n </I> indicates the WordNet sense number of the term pointed 
+to. <P>
+ The <B>"Domain" </B> and <B>"Domain Terms" </B> searches show the domain that a 
+synset has been classified in and, conversely, all of the terms that have 
+been assigned to a specific domain.  A domain is either a <B>TOPIC, </B> <B>REGION 
+</B> or <B>USAGE, </B> as reflected in the specific pointer character stored in the 
+database, and displayed in the output.  A <B>Domain </B> search on a term shows 
+the domain, if any, that each synset containing <I>searchstr </I> has been classified 
+in.  The output display shows the domain type (<B>TOPIC, </B> <B>REGION </B> or <B>USAGE 
+</B>), followed by the syntactic category of the domain synset and the terms 
+in the synset.  Each term is followed by <B># </B><I>n </I> where <I>n </I> indicates the WordNet 
+sense number of the term.  The converse search, <B>Domain Terms </B>, shows all 
+of the synsets that have been placed into the domain <I>searchstr </I>, with 
+analogous markers.  <P>
+ When the <B>"Sentence Frames" </B> search is specified, sample 
+illustrative sentences and generic sentence frames are displayed.  If a 
+sample sentence is found, the base form of the search word is substituted 
+into the sentence, and it is printed below the synset, preceded with the 
+<B>EX: </B> marker.  When no sample sentences are found, the generic sentence 
+frames are displayed.  Sentence frames that are acceptable for all words 
+in a synset are preceded by the marker <B>*&gt; </B>.  If a frame is acceptable for 
+the search word only, it is preceded by the marker <B>=&gt; </B>. <P>
+ Search results 
+for adjectives are slightly different from those for other parts of speech. 
+ When an adjective is printed, its direct antonym, if it has one, is also 
+printed in parentheses.  When the search word is in a head synset, all 
+of the head synset's satellites are also displayed.  The position of an 
+adjective in relation to the noun may be restricted to the <I>prenominal 
+</I>, <I>postnominal </I> or <I>predicative </I> position.  Where present, these restrictions 
+are noted in parentheses. <P>
+ When an adjective is a participle of a verb, 
+the output indicates the verb and displays its synset. <P>
+ When an adverb 
+is derived from an adjective, the specific adjectival sense on which it 
+is based is indicated. <P>
+ The morphological transformations performed by 
+the search code may result in more than one word to search for.  <B>wnb() 
+</B> automatically performs the requested search on all of the strings and 
+returns the results grouped by word.  For example, the verb <B>saw </B> is both 
+the present tense of <B>saw </B> and the past tense of <B>see </B>.  When there is more 
+than one word to search for, search results are grouped by word.  </blockquote>
+ 
+<H2><A NAME="sect14" HREF="#toc14">DIAGNOSTICS 
+</A></H2>
+If the WordNet database files cannot be opened, error messages are displayed. 
+ This is usually corrected by setting the environment variables described 
+below to the proper location of the WordNet database for your installation. 
+ 
+<H2><A NAME="sect15" HREF="#toc15">ENVIRONMENT VARIABLES (UNIX) </A></H2>
+
+<DL>
+
+<DT><B>WNHOME</B>  </DT>
+<DD>Base directory for WordNet.  Default 
+is <B>/usr/local/WordNet-3.0 </B>. </DD>
+
+<DT><B>WNSEARCHDIR</B>  </DT>
+<DD>Directory in which the WordNet database 
+has been installed.   Default is <B>WNHOME/dict </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect16" HREF="#toc16">REGISTRY (WINDOWS) </A></H2>
+
+<DL>
+
+<DT><B>HKEY_LOCAL_MACHINE\SOFTWARE\WordNet\3.0\WNHome</B> 
+ </DT>
+<DD>Base directory for WordNet.  Default is <B>C:\Program&nbsp;Files\WordNet\3.0 </B>. </DD>
+
+<DT><B>HKEY_CURRENT_USER\SOFTWARE\WordNet\3.0\wnres</B> 
+ </DT>
+<DD>User's default browser options. </DD>
+</DL>
+ 
+<H2><A NAME="sect17" HREF="#toc17">FILES </A></H2>
+
+<DL>
+
+<DT><B>index.<I>pos </I></B>  </DT>
+<DD>database index files 
+</DD>
+
+<DT><B>data.<I>pos </I></B>  </DT>
+<DD>database data files </DD>
+
+<DT><B>*.vrb</B>  </DT>
+<DD>files of sentences illustrating the 
+use of verbs </DD>
+
+<DT><B><I>pos </I>.exc</B>  </DT>
+<DD>morphology exception lists </DD>
+</DL>
+ 
+<H2><A NAME="sect18" HREF="#toc18">SEE ALSO </A></H2>
+<B><A HREF="wnintro.1WN.html">wnintro</B>(1WN)</A>
+, 
+<B><A HREF="wn.1WN.html">wn</B>(1WN)</A>
+, <B><A HREF="wnintro.3WN.html">wnintro</B>(3WN)</A>
+, <B><A HREF="lexnames.5WN.html">lexnames</B>(5WN)</A>
+, <B><A HREF="senseidx.5WN.html">senseidx</B>(5WN)</A>
+, <B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+,<B></B> <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+, 
+<B><A HREF="morphy.7WN.html">morphy</B>(7WN)</A>
+,<B></B> <B><A HREF="wngloss.7WN.html">wngloss</B>(7WN)</A>
+, <B><A HREF="wngroups.7WN.html">wngroups</B>(7WN)</A>
+.  
+<H2><A NAME="sect19" HREF="#toc19">BUGS </A></H2>
+Please reports bugs to 
+wordnet@princeton.edu. <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">SYNOPSIS</A></LI>
+<LI><A NAME="toc2" HREF="#sect2">DESCRIPTION</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">WNB WINDOWS</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">SEARCHING THE DATABASE</A></LI>
+<UL>
+<LI><A NAME="toc5" HREF="#sect5">Changing the Search Word</A></LI>
+<LI><A NAME="toc6" HREF="#sect6">Interrupting a Search</A></LI>
+</UL>
+<LI><A NAME="toc7" HREF="#sect7">MENUS</A></LI>
+<UL>
+<LI><A NAME="toc8" HREF="#sect8">File Menu</A></LI>
+<LI><A NAME="toc9" HREF="#sect9">History</A></LI>
+<LI><A NAME="toc10" HREF="#sect10">Options</A></LI>
+<LI><A NAME="toc11" HREF="#sect11">Help</A></LI>
+</UL>
+<LI><A NAME="toc12" HREF="#sect12">SHORCUTS</A></LI>
+<LI><A NAME="toc13" HREF="#sect13">SEARCH RESULTS</A></LI>
+<LI><A NAME="toc14" HREF="#sect14">DIAGNOSTICS</A></LI>
+<LI><A NAME="toc15" HREF="#sect15">ENVIRONMENT VARIABLES (UNIX)</A></LI>
+<LI><A NAME="toc16" HREF="#sect16">REGISTRY (WINDOWS)</A></LI>
+<LI><A NAME="toc17" HREF="#sect17">FILES</A></LI>
+<LI><A NAME="toc18" HREF="#sect18">SEE ALSO</A></LI>
+<LI><A NAME="toc19" HREF="#sect19">BUGS</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wndb.5WN.html

@@ -0,0 +1,398 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WNDB(5WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+index.noun, data.noun, index.verb, data.verb, index.adj, data.adj, index.adv, 
+data.adv - WordNet database files <P>
+noun.exc, verb.exc. adj.exc adv.exc - morphology 
+exception lists <P>
+sentidx.vrb, sents.vrb - files used by search code to display 
+sentences illustrating the use of some specific verbs  
+<H2><A NAME="sect1" HREF="#toc1">DESCRIPTION </A></H2>
+For 
+each syntactic category, two files are needed to represent the contents 
+of the WordNet database - <B>index. </B><I>pos </I> and <B>data. </B><I>pos </I>, where <I>pos </I> is <B>noun 
+</B>, <B>verb </B>, <B>adj </B> and <B>adv </B>.  The other auxiliary files are used by the WordNet 
+library's searching functions and are needed to run the various WordNet 
+browsers. <P>
+ Each index file is an alphabetized list of all the words found 
+in WordNet in the corresponding part of speech.  On each line, following 
+the word, is a list of byte offsets (<I>synset_offset </I>s) in the corresponding 
+data file, one for each synset containing the word. Words in the index 
+file are in lower case only, regardless of how they were entered in the 
+lexicographer files.  This folds various orthographic representations of 
+the word into one line enabling database searches to be case insensitive. 
+ See <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+ for a detailed description of the lexicographer files 
+<P>
+ A data file for a syntactic category contains information corresponding 
+to the synsets that were specified in the lexicographer files, with relational 
+pointers resolved to <I>synset_offset </I>s. Each line corresponds to a synset. 
+ Pointers are followed and hierarchies traversed by moving from one synset 
+to another via the <I>synset_offset </I>s.   <P>
+ The exception list files, <I>pos </I><B>.exc 
+</B>, are used to help the morphological processor find base forms from irregular 
+inflections. <P>
+ The files <B>sentidx.vrb </B> and <B>sents.vrb </B> contain sentences illustrating 
+the use of specific senses of some verbs.  These files are used by the 
+searching software in response to a request for verb sentence frames.  
+Generic sentence frames are displayed when an illustrative sentence is 
+not present. <P>
+ The various database files are in ASCII formats that are 
+easily read by both humans and machines.  All fields, unless otherwise 
+noted, are separated by one space character, and all lines are terminated 
+by a newline character.  Fields enclosed in italicized square brackets 
+may not be present. <P>
+ See  <B><A HREF="wngloss.7WN.html">wngloss</B>(7WN)</A>
+ for a glossary of WordNet terminology 
+and a discussion of the database's content and logical organization.  
+<H3><A NAME="sect2" HREF="#toc2">Index 
+File Format </A></H3>
+Each index file begins with several lines containing a copyright 
+notice, version number and license agreement.  These lines all begin with 
+two spaces and the line number so they do not interfere with the binary 
+search algorithm that is used to look up entries in the index files.  All 
+other lines are in the following format.  In the field descriptions, <B>number 
+</B> always refers to a decimal integer unless otherwise defined. <P>
+ <I>lemma&nbsp;&nbsp;pos&nbsp;&nbsp;synset_cnt&nbsp;&nbsp;p_cnt&nbsp;&nbsp;[ptr_symbol...]&nbsp;&nbsp;sense_cnt&nbsp;&nbsp;tagsense_cnt 
+&nbsp;&nbsp;synset_offset&nbsp;&nbsp;[synset_offset...] </I> <BR>
+ <P>
+ 
+<DL>
+
+<DT><I>lemma</I>  </DT>
+<DD>lower case ASCII text of word 
+or collocation.  Collocations are formed by joining individual words with 
+an underscore (<B>_ </B>) character. </DD>
+
+<DT><I>pos</I>  </DT>
+<DD>Syntactic category: <B>n </B> for noun files, 
+ <B>v </B> for verb files, <B>a </B> for adjective files, <B>r </B> for adverb files. </DD>
+</DL>
+<P>
+ <P>
+All remaining 
+fields are with respect to senses of <I>lemma </I> in <I>pos </I>. <P>
+ 
+<DL>
+
+<DT><I>synset_cnt</I>  </DT>
+<DD>Number 
+of synsets that <I>lemma </I> is in.  This is the number of senses of the word 
+in WordNet. See  <FONT SIZE=-1><B>Sense Numbers </B></FONT>
+ below for a discussion of how sense numbers 
+are assigned and the order of <I>synset_offset </I>s in the index files. </DD>
+
+<DT><I>p_cnt</I> 
+ </DT>
+<DD>Number of different pointers that <I>lemma </I> has in all synsets containing 
+it. </DD>
+
+<DT><I>ptr_symbol</I>  </DT>
+<DD>A space separated list of <I>p_cnt </I> different types of pointers 
+that <I>lemma </I> has in all synsets containing it. See <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+ for a list 
+of <I>pointer_symbol </I>s.  If all senses of <I>lemma </I> have no pointers, this field 
+is omitted and <I>p_cnt </I> is <B>0 </B>. </DD>
+
+<DT><I>sense_cnt</I>  </DT>
+<DD>Same as <I>sense_cnt </I> above.  This 
+is redundant, but the field was preserved for compatibility reasons. </DD>
+
+<DT><I>tagsense_cnt</I> 
+ </DT>
+<DD>Number of senses of <I>lemma </I> that are ranked according to their frequency 
+of occurrence in semantic concordance texts. </DD>
+
+<DT><I>synset_offset</I>  </DT>
+<DD>Byte offset 
+in <B>data.<I>pos </I></B> file of a synset containing <I>lemma </I>.  Each <I>synset_offset </I> in 
+the list corresponds to a different sense of <I>lemma </I> in WordNet.  <I>synset_offset 
+</I> is an 8 digit, zero-filled decimal integer that can be used with <B><A HREF="fseek.3.html">fseek</B>(3)</A>
+ 
+to read a synset from the data file.  When passed to <B><A HREF="read_synset.3WN.html">read_synset</B>(3WN)</A>
+ along 
+with the syntactic category, a data structure containing the parsed synset 
+is returned. </DD>
+</DL>
+ 
+<H3><A NAME="sect3" HREF="#toc3">Data File Format </A></H3>
+Each data file begins with several lines 
+containing a copyright notice, version number and license agreement.  These 
+lines all begin with two spaces and the line number.  All other lines are 
+in the following format.  Integer fields are of fixed length, and are zero-filled. 
+<P>
+ <I>synset_offset&nbsp;&nbsp;lex_filenum&nbsp;&nbsp;ss_type&nbsp;&nbsp;w_cnt&nbsp;&nbsp;word&nbsp;&nbsp;lex_id&nbsp;&nbsp;[word&nbsp;&nbsp;lex_id...]&nbsp;&nbsp;p_cnt&nbsp;&nbsp;[ptr...]&nbsp;&nbsp;[frames...]&nbsp;&nbsp;<B>| 
+</B></I><I>&nbsp;&nbsp;gloss </I> <BR>
+ <P>
+ 
+<DL>
+
+<DT><I>synset_offset</I>  </DT>
+<DD>Current byte offset in the file represented 
+as an 8 digit decimal integer.  </DD>
+
+<DT><I>lex_filenum</I>  </DT>
+<DD>Two digit decimal integer 
+corresponding to the lexicographer file name containing the synset.  See 
+<B><A HREF="lexnames.5WN.html">lexnames</B>(5WN)</A>
+ for the list of filenames and their corresponding numbers. 
+</DD>
+
+<DT><I>ss_type</I>  </DT>
+<DD>One character code indicating the synset type:  </DD>
+</DL>
+<P>
+  <blockquote><B>n </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;NOUN <BR>
+ <B>v </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;VERB 
+<BR>
+ <B>a </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADJECTIVE <BR>
+ <B>s </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADJECTIVE SATELLITE <BR>
+ <B>r </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADVERB <BR>
+  </blockquote>
+
+<DL>
+
+<DT><I>w_cnt</I>  </DT>
+<DD>Two digit hexadecimal 
+integer indicating the number of words in the synset. </DD>
+
+<DT><I>word</I>  </DT>
+<DD>ASCII form 
+of a word as entered in the synset by the lexicographer, with spaces replaced 
+by underscore characters (<B>_ </B>).  The text of the word is case sensitive, 
+in contrast to its form in the corresponding <B>index. </B><I>pos </I> file, that contains 
+only lower-case forms.  In <B>data.adj </B>, a <I>word </I> is followed by a syntactic 
+marker if one was specified in the lexicographer file.  A syntactic marker 
+is appended, in parentheses, onto <I>word </I> without any intervening spaces. 
+ See <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+ for a list of the syntactic markers for adjectives. </DD>
+
+<DT><I>lex_id</I> 
+ </DT>
+<DD>One digit hexadecimal integer that, when appended onto <I>lemma </I>, uniquely 
+identifies a sense within a lexicographer file.  <I>lex_id </I> numbers usually 
+start with <B>0 </B>, and are incremented as additional senses of the word are 
+added to the same file, although there is no requirement that the numbers 
+be consecutive or begin with <B>0 </B>. Note that a value of <B>0 </B> is the default, 
+and therefore is not present in lexicographer files.  </DD>
+
+<DT><I>p_cnt</I>  </DT>
+<DD>Three digit 
+decimal integer indicating the number of pointers from this synset to 
+other synsets.  If <I>p_cnt </I> is <B>000 </B> the synset has no pointers. </DD>
+
+<DT><I>ptr</I>  </DT>
+<DD>A pointer 
+from this synset to another.  <I>ptr </I> is of the form: </DD>
+</DL>
+<P>
+ <I>pointer_symbol&nbsp;&nbsp;synset_offset&nbsp;&nbsp;pos&nbsp;&nbsp;source/target 
+</I> <BR>
+ <P>
+ where <I>synset_offset </I> is the byte offset of the target synset in the 
+data file corresponding to <I>pos </I>. <P>
+ The <I>source/target </I> field distinguishes 
+lexical and semantic pointers.  It is a four byte field, containing two 
+two-digit hexadecimal integers.  The first two digits indicates the word 
+number in the current (source) synset, the last two digits indicate the 
+word number in the target synset.  A value of <B>0000 </B> means that <I>pointer_symbol 
+</I> represents a semantic relation between the current (source) synset and 
+the target synset indicated by <I>synset_offset </I>. <P>
+ A lexical relation between 
+two words in different synsets is represented by non-zero values in the 
+source and target word numbers. The first and last two bytes of this field 
+indicate the word numbers in the source and target synsets, respectively, 
+between which the relation holds.  Word numbers are assigned to the <I>word 
+</I> fields in a synset, from left to right, beginning with <B>1 </B>. <P>
+ See  <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+ 
+for a list of <I>pointer_symbol </I>s, and semantic and lexical pointer classifications. 
+
+<DL>
+
+<DT><I>frames</I>  </DT>
+<DD>In <B>data.verb </B> only, a list of numbers corresponding to the generic 
+verb sentence frames for <I>word </I>s in the synset.   <I>frames </I> is of the form: 
+</DD>
+</DL>
+<P>
+ <I>f_cnt&nbsp;&nbsp; </I> <B>+ </B> <I>&nbsp;&nbsp;f_num&nbsp;&nbsp;w_num&nbsp;&nbsp;[ </I> <B>+ </B> <I>&nbsp;&nbsp;f_num&nbsp;&nbsp;w_num...] </I> <BR>
+ <P>
+ where <I>f_cnt </I> a two 
+digit decimal integer indicating the number of generic frames listed, 
+<I>f_num </I> is a two digit decimal integer frame number, and <I>w_num </I> is a two 
+digit hexadecimal integer indicating the word in the synset that the frame 
+applies to.  As with pointers, if this number is <B>00 </B>, <I>f_num </I> applies to 
+all <I>word </I>s in the synset.  If non-zero, it is applicable only to the word 
+indicated.  Word numbers are assigned as described for pointers. Each <I>f_num&nbsp;&nbsp;w_num 
+</I> pair is preceded by a <B>+ </B>. See <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+ for the text of the generic 
+sentence frames. 
+<DL>
+
+<DT><I>gloss</I>  </DT>
+<DD>Each synset contains a gloss.  A <I>gloss </I> is represented 
+as a vertical bar (<B>| </B>), followed by a text string that continues until 
+the end of the line.  The gloss may contain a definition, one or more example 
+sentences, or both. </DD>
+</DL>
+ 
+<H3><A NAME="sect4" HREF="#toc4">Sense Numbers </A></H3>
+Senses in WordNet are generally ordered 
+from most to least frequently used, with the most common sense numbered 
+<B>1 </B>.  Frequency of use is determined by the number of times a sense is tagged 
+in the various semantic concordance texts.  Senses that are not semantically 
+tagged follow the ordered senses.  The <I>tagsense_cnt </I> field for each entry 
+in the <B>index.<I>pos </I></B> files indicates how many of the senses in the list have 
+been tagged. <P>
+ The  <B><A HREF="cntlist.5WN.html">cntlist</B>(5WN)</A>
+ file provided with the database lists the 
+number of times each sense is tagged in the semantic concordances.  The 
+data from <B>cntlist </B> is used by <B><A HREF="grind.1WN.html">grind</B>(1WN)</A>
+ to order the senses of each word. 
+ When the <B>index </B>.<I>pos </I> files are generated, the <I>synset_offset </I>s are output 
+in sense number order, with sense 1 first in the list.  Senses with the 
+same number of semantic tags are assigned unique but consecutive sense 
+numbers.  The WordNet  <FONT SIZE=-1><B>OVERVIEW </B></FONT>
+  search displays all senses of the specified 
+word, in all syntactic categories, and indicates which of the senses are 
+represented in the semantically tagged texts.  
+<H3><A NAME="sect5" HREF="#toc5">Exception List File Format 
+</A></H3>
+Exception lists are alphabetized lists of inflected forms of words and 
+their base forms.  The first field of each line is an inflected form, followed 
+by a space separated list of one or more base forms of the word.  There 
+is one exception list file for each syntactic category. <P>
+ Note that the 
+noun and verb exception lists were automatically generated from a machine-readable 
+dictionary, and contain many words that are not in WordNet.  Also, for 
+many of the inflected forms, base forms could be easily derived using 
+the standard rules of detachment programmed into Morphy (See <B><A HREF="morph.7WN.html">morph</B>(7WN)</A>
+). 
+These anomalies are allowed to remain in the exception list files, as 
+they do no harm. <P>
+  
+<H3><A NAME="sect6" HREF="#toc6">Verb Example Sentences </A></H3>
+For some verb senses, example 
+sentences illustrating the use of the verb sense can be displayed.  Each 
+line of the file <B>sentidx.vrb </B> contains a <I>sense_key </I> followed by a space 
+and a comma separated list of example sentence template numbers, in decimal. 
+ The file <B>sents.vrb </B> lists all of the example sentence templates.  Each 
+line begins with the template number followed by a space.  The rest of 
+the line is the text of a template example sentence, with <B>%s </B> used as 
+a placeholder in the text for the verb.  Both files are sorted alphabetically 
+so that the <I>sense_key </I> and template sentence number can be used as indices, 
+via <B><A HREF="binsrch.3WN.html">binsrch</B>(3WN)</A>
+,<B></B> into the appropriate file. <P>
+ When a request for  <FONT SIZE=-1><B>FRAMES 
+</B></FONT>
+  is made, the WordNet search code looks for the sense in <B>sentidx.vrb </B>. 
+ If found, the sentence template(s) listed is retrieved from <B>sents.vrb 
+</B>, and the <B>%s </B> is replaced with the verb.  If the sense is not found, the 
+applicable generic sentence frame(s) listed in <I>frames </I> is displayed.  
+<H2><A NAME="sect7" HREF="#toc7">NOTES 
+</A></H2>
+Information in the <B>data.<I>pos </I></B> and <B>index.<I>pos </I></B> files represents all of the 
+word senses and synsets in the WordNet database. The <I>word </I>, <I>lex_id </I>, and 
+<I>lex_filenum </I> fields together uniquely identify each word sense in WordNet. 
+ These can be encoded in a <I>sense_key </I> as described in <B><A HREF="senseidx.5WN.html">senseidx</B>(5WN)</A>
+. Each 
+synset in the database can be uniquely identified by combining the <I>synset_offset 
+</I> for the synset with a code for the syntactic category (since it is possible 
+for synsets in different <B>data.<I>pos </I></B> files to have the same <I>synset_offset 
+</I>). <P>
+ The WordNet system provide both command line and window-based browser 
+interfaces to the database.  Both interfaces utilize a common library of 
+search and morphology code.  The source code for the library and interfaces 
+is included in the WordNet package.  See <B><A HREF="wnintro.3WN.html">wnintro</B>(3WN)</A>
+ for an overview of 
+the WordNet source code.  
+<H2><A NAME="sect8" HREF="#toc8">ENVIRONMENT VARIABLES (UNIX) </A></H2>
+
+<DL>
+
+<DT><B>WNHOME</B>  </DT>
+<DD>Base directory 
+for WordNet.  Default is <B>/usr/local/WordNet-3.0 </B>. </DD>
+
+<DT><B>WNSEARCHDIR</B>  </DT>
+<DD>Directory in 
+which the WordNet database has been installed.   Default is <B>WNHOME/dict 
+</B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect9" HREF="#toc9">REGISTRY (WINDOWS) </A></H2>
+
+<DL>
+
+<DT><B>HKEY_LOCAL_MACHINE\SOFTWARE\WordNet\3.0\WNHome</B>  </DT>
+<DD>Base directory 
+for WordNet.  Default is <B>C:\Program&nbsp;Files\WordNet\3.0 </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect10" HREF="#toc10">FILES </A></H2>
+
+<DL>
+
+<DT><B>index.<I>pos </I></B>  </DT>
+<DD>database 
+index files </DD>
+
+<DT><B>data.<I>pos </I></B>  </DT>
+<DD>database data files </DD>
+
+<DT><B>*.vrb</B>  </DT>
+<DD>files of sentences illustrating 
+the use of verbs </DD>
+
+<DT><B><I>pos </I>.exc</B>  </DT>
+<DD>morphology exception lists </DD>
+</DL>
+ 
+<H2><A NAME="sect11" HREF="#toc11">SEE ALSO </A></H2>
+<B><A HREF="grind.1WN.html">grind</B>(1WN)</A>
+, 
+<B><A HREF="wn.1WN.html">wn</B>(1WN)</A>
+, <B><A HREF="wnb.1WN.html">wnb</B>(1WN)</A>
+, <B><A HREF="wnintro.3WN.html">wnintro</B>(3WN)</A>
+, <B><A HREF="binsrch.3WN.html">binsrch</B>(3WN)</A>
+, <B><A HREF="wnintro.5WN.html">wnintro</B>(5WN)</A>
+, <B><A HREF="cntlist.5WN.html">cntlist</B>(5WN)</A>
+, 
+<B><A HREF="lexnames.5WN.html">lexnames</B>(5WN)</A>
+, <B><A HREF="senseidx.5WN.html">senseidx</B>(5WN)</A>
+, <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+, <B><A HREF="morphy.7WN.html">morphy</B>(7WN)</A>
+, <B><A HREF="wngloss.7WN.html">wngloss</B>(7WN)</A>
+, 
+<B><A HREF="wngroups.7WN.html">wngroups</B>(7WN)</A>
+, <B><A HREF="wnstats.7WN.html">wnstats</B>(7WN)</A>
+. <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">DESCRIPTION</A></LI>
+<UL>
+<LI><A NAME="toc2" HREF="#sect2">Index File Format</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">Data File Format</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">Sense Numbers</A></LI>
+<LI><A NAME="toc5" HREF="#sect5">Exception List File Format</A></LI>
+<LI><A NAME="toc6" HREF="#sect6">Verb Example Sentences</A></LI>
+</UL>
+<LI><A NAME="toc7" HREF="#sect7">NOTES</A></LI>
+<LI><A NAME="toc8" HREF="#sect8">ENVIRONMENT VARIABLES (UNIX)</A></LI>
+<LI><A NAME="toc9" HREF="#sect9">REGISTRY (WINDOWS)</A></LI>
+<LI><A NAME="toc10" HREF="#sect10">FILES</A></LI>
+<LI><A NAME="toc11" HREF="#sect11">SEE ALSO</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wngloss.7WN.html

@@ -0,0 +1,325 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WNGLOSS(7WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+wngloss - glossary of terms used in WordNet system  
+<H2><A NAME="sect1" HREF="#toc1">DESCRIPTION 
+</A></H2>
+The <I>WordNet Reference Manual </I> consists of Unix-style manual pages divided 
+into sections as follows: <P>
+  <TABLE BORDER=0>
+ <TR> <TD ALIGN=CENTER><B>Section </B> </TD> <TD ALIGN=CENTER><B>Description </B> </TD> </TR>
+ <TR>  <TR> <TD ALIGN=CENTER>1 </TD> <TD ALIGN=LEFT>WordNet User 
+Commands </TD> </TR>
+ <TR> <TD ALIGN=CENTER>3 </TD> <TD ALIGN=LEFT>WordNet Library Functions </TD> </TR>
+ <TR> <TD ALIGN=CENTER>5 </TD> <TD ALIGN=LEFT>WordNet File Formats </TD> </TR>
+ 
+<TR> <TD ALIGN=CENTER>7 </TD> <TD ALIGN=LEFT>Miscellaneous Information about WordNet </TD> </TR>
+ </TABLE>
+<P>
+  
+<H3><A NAME="sect2" HREF="#toc2">System Description </A></H3>
+The 
+WordNet system consists of lexicographer files, code to convert these 
+files into a database, and search routines and interfaces that display 
+information from the database.  The lexicographer files organize nouns, 
+verbs, adjectives and adverbs into groups of synonyms, and describe relations 
+between synonym groups. <B><A HREF="grind.1WN.html">grind</B>(1WN)</A>
+ converts the lexicographer files into 
+a database that encodes the relations between the synonym groups.  The 
+different interfaces to the WordNet database utilize a common library 
+of search routines to display these relations.  Note that the lexicographer 
+files and  <B><A HREF="grind.1WN.html">grind</B>(1WN)</A>
+ program are not generally distributed.   <P>
+  
+<H3><A NAME="sect3" HREF="#toc3">Database 
+Organization </A></H3>
+Information in WordNet is organized around logical groupings 
+called synsets.  Each synset consists of a list of synonymous words or 
+collocations (eg. <B>"fountain pen" </B>, <B>"take in" </B>), and pointers that describe 
+the relations between this synset and other synsets.  A word or collocation 
+may appear in more than one synset, and in more than one part of speech. 
+ The words in a synset are grouped such that they are interchangeable 
+in some context. <P>
+ Two kinds of relations are represented by pointers: lexical 
+and semantic.  Lexical relations hold between semantically related  word 
+forms; semantic relations hold between word meanings.  These relations 
+include (but are not limited to) hypernymy/hyponymy (superordinate/subordinate), 
+ antonymy, entailment, and meronymy/holonymy. <P>
+ Nouns and verbs are organized 
+into hierarchies based on the hypernymy/hyponymy relation between synsets. 
+ Additional pointers are be used to indicate other relations.   <P>
+ Adjectives 
+are arranged in clusters containing head synsets and satellite synsets. 
+ Each cluster is organized around antonymous pairs (and occasionally antonymous 
+triplets).  The antonymous pairs (or triplets) are indicated in the head 
+synsets of a cluster.  Most head synsets have one or more satellite synsets, 
+each of which represents a concept that is similar in meaning to the concept 
+represented by the head synset.  One way to think of the adjective cluster 
+organization is to visualize a wheel, with a head synset as the hub and 
+satellite synsets as the spokes.  Two or more wheels are logically connected 
+via antonymy, which can be thought of as an axle between the wheels. <P>
+ Pertainyms 
+are relational adjectives and do not follow the structure just described. 
+ Pertainyms do not have antonyms; the synset for a pertainym most often 
+contains only one word or collocation and a lexical pointer to the noun 
+that the adjective is "pertaining to".  Participial adjectives have lexical 
+pointers to the verbs that they are derived from. <P>
+ Adverbs are often derived 
+from adjectives, and sometimes have antonyms; therefore the synset for 
+an adverb usually contains a lexical pointer to the adjective from which 
+it is derived. <P>
+ See <B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+ for a detailed description of the database 
+files and how the data are represented.   
+<H2><A NAME="sect4" HREF="#toc4">GLOSSARY OF TERMS </A></H2>
+Many terms 
+used in the <I>WordNet Reference Manual </I> are unique to the WordNet system. 
+ Other general terms have specific meanings when used in the WordNet documentation. 
+ Definitions for many of these terms are given to help with the interpretation 
+and understanding of the reference manual, and in the use of the WordNet 
+system. <P>
+ In following definitions <B>word </B> is used in place of <B>word or collocation 
+</B>. 
+<DL>
+
+<DT><B>adjective cluster</B>  </DT>
+<DD>A group of adjective synsets that are organized around 
+antonymous pairs or triplets.  An adjective cluster contains two or more 
+<B>head synsets </B> which represent antonymous concepts. Each head synset has 
+one or more <B>satellite synsets </B>. </DD>
+
+<DT><B>attribute</B>  </DT>
+<DD>A noun for which adjectives 
+express values. The noun <B>weight </B> is an attribute, for which the adjectives 
+ <B>light </B> and <B>heavy </B> express values.  </DD>
+
+<DT><B>base form</B>  </DT>
+<DD>The base form of a word 
+or collocation is the form to which inflections are added. </DD>
+
+<DT><B>basic synset</B> 
+ </DT>
+<DD>Syntactically, same as <B>synset </B>.  Term is used in  <B><A HREF="wninput.5WN.html">wninput</B>(5WN)<B></B></A>
+ to help 
+explain differences in entering synsets in lexicographer files. </DD>
+
+<DT><B>collocation</B> 
+ </DT>
+<DD>A collocation in WordNet is a string of two or more words, connected 
+by spaces or hyphens.  Examples are: <B>man-eating&nbsp;shark </B>, <B>blue-collar </B>, <B>depend&nbsp;on 
+</B>, <B>line&nbsp;of&nbsp;products </B>.  In the database files spaces are represented as underscore 
+(<B>_ </B>) characters. </DD>
+
+<DT><B>coordinate</B>  </DT>
+<DD>Coordinate terms are nouns or verbs that have 
+the same <B>hypernym </B>. </DD>
+
+<DT><B>cross-cluster pointer</B>  </DT>
+<DD>A <B>semantic pointer </B> from one 
+adjective cluster to another. </DD>
+
+<DT><B>derivationally related forms</B>  </DT>
+<DD>Terms in different 
+syntactic categories that have the same root form and are semantically 
+related.  </DD>
+
+<DT><B>direct antonyms</B>  </DT>
+<DD>A pair of words between which there is an associative 
+bond resulting from their frequent co-occurrence.  In <B>adjective clusters 
+</B>, direct antonyms appears only in <B>head synsets </B>. </DD>
+
+<DT><B>domain</B>  </DT>
+<DD>A topical classification 
+to which a synset has been linked with a CATEGORY, REGION or USAGE pointer. 
+</DD>
+
+<DT><B>domain term</B>  </DT>
+<DD>A synset belonging to a topical class.  A domain term is further 
+identified as being a CATEGORY_TERM, REGION_TERM or USAGE_TERM. </DD>
+
+<DT><B>entailment</B> 
+ </DT>
+<DD>A verb <B>X </B> entails <B>Y </B> if <B>X </B> cannot be done unless <B>Y </B> is,  or has been, 
+done. </DD>
+
+<DT><B>exception list</B>  </DT>
+<DD>Morphological transformations for words that are 
+not regular and therefore cannot be processed in an algorithmic manner. 
+</DD>
+
+<DT><B>group</B>  </DT>
+<DD>Verb senses that similar in meaning and have been manually grouped 
+together. </DD>
+
+<DT><B>gloss</B>  </DT>
+<DD>Each synset contains <B>gloss </B> consisting of a definition 
+and optionally example sentences. </DD>
+
+<DT><B>head synset</B>  </DT>
+<DD>Synset in an adjective <B>cluster 
+</B> containing at least one word that has a <B>direct antonym </B>. </DD>
+
+<DT><B>holonym</B>  </DT>
+<DD>The 
+name of the whole of which the meronym names a part.  <B>Y </B>  is a holonym 
+of <B>X </B> if <B>X </B> is a part of <B>Y </B>. </DD>
+
+<DT><B>hypernym</B>  </DT>
+<DD>The generic term used to designate 
+a whole class of specific instances. <B>Y </B> is a hypernym of <B>X </B> if <B>X </B> is a 
+(kind of) <B>Y </B>.   </DD>
+
+<DT><B>hyponym</B>  </DT>
+<DD>The specific term used to designate a member of 
+a class.  <B>X </B> is a hyponym of  <B>Y </B> if <B>X </B> is a (kind of) <B>Y </B>. </DD>
+
+<DT><B>indirect antonym</B> 
+ </DT>
+<DD>An adjective in a <B>satellite synset </B> that does not have a <B>direct antonym 
+</B> has an indirect antonyms via the direct antonym of the <B>head synset </B>. </DD>
+
+<DT><B>instance</B> 
+ </DT>
+<DD>A proper noun that refers to a particular, unique referent (as distinguished 
+from nouns that refer to classes).  This is a specific form of hyponym. 
+</DD>
+
+<DT><B>lemma</B>  </DT>
+<DD>Lower case ASCII text of word as found in the WordNet database 
+index files.  Usually the <B>base form </B> for a word or collocation. </DD>
+
+<DT><B>lexical 
+pointer</B>  </DT>
+<DD>A lexical pointer indicates a relation between words in synsets 
+(word forms). </DD>
+
+<DT><B>lexicographer file</B>  </DT>
+<DD>Files containing the raw data for WordNet 
+synsets, edited by lexicographers, that are input to the <B>grind </B> program 
+to generate a WordNet database. </DD>
+
+<DT><B>lexicographer id (lex id)</B>  </DT>
+<DD>A decimal integer 
+that, when appended onto <B>lemma </B>, uniquely identifies a sense within a 
+lexicographer file.  </DD>
+
+<DT><B>monosemous</B>  </DT>
+<DD>Having only one sense in a syntactic category. 
+</DD>
+
+<DT><B>meronym</B>  </DT>
+<DD>The name of a constituent part of, the substance of, or a member 
+of something.  <B>X </B> is a meronym of <B>Y </B> if <B>X </B> is a part of <B>Y </B>. </DD>
+
+<DT><B>part of speech</B> 
+ </DT>
+<DD>WordNet defines "part of speech" as either noun, verb, adjective, or 
+adverb.  Same as <B>syntactic category </B>. </DD>
+
+<DT><B>participial adjective</B>  </DT>
+<DD>An adjective 
+that is derived from a verb. </DD>
+
+<DT><B>pertainym</B>  </DT>
+<DD>A relational adjective.  Adjectives 
+that are pertainyms are usually defined by such phrases as "of or pertaining 
+to" and do not have antonyms.  A pertainym can point to a noun or another 
+pertainym. </DD>
+
+<DT><B>polysemous</B>  </DT>
+<DD>Having more than one sense in a syntactic category. 
+</DD>
+
+<DT><B>polysemy count</B>  </DT>
+<DD>Number of senses of a word in a syntactic category, in 
+WordNet. </DD>
+
+<DT><B>postnominal</B>  </DT>
+<DD>A postnominal adjective occurs only immediately following 
+the noun  that it modifies. </DD>
+
+<DT><B>predicative</B>  </DT>
+<DD>An adjective that can be used 
+only in predicate positions.  If <B>X </B> is a predicate adjective, it can only 
+be used in such phrases as "it is <B>X </B>" and never prenominally. </DD>
+
+<DT><B>prenominal</B> 
+ </DT>
+<DD>An adjective that can occur only before the noun that it modifies: it 
+cannot be used predicatively. </DD>
+
+<DT><B>satellite synset</B>  </DT>
+<DD>Synset in an adjective 
+<B>cluster </B> representing a concept that is similar in meaning to the concept 
+represented by its <B>head synset </B>. </DD>
+
+<DT><B>semantic concordance</B>  </DT>
+<DD>A textual corpus 
+(e.g. the Brown Corpus) and a lexicon (e.g. WordNet) so combined  that every 
+substantive word in the text is linked to its appropriate sense in the 
+lexicon via a <B>semantic tag </B>. </DD>
+
+<DT><B>semantic tag</B>  </DT>
+<DD>A pointer from a word in a text 
+file to a specific sense of that word in the WordNet database.  A semantic 
+tag in a semantic concordance is represented by a <B>sense key </B>. </DD>
+
+<DT><B>semantic 
+pointer</B>  </DT>
+<DD>A semantic pointer indicates a relation between synsets (concepts). 
+</DD>
+
+<DT><B>sense</B>  </DT>
+<DD>A meaning of a word in WordNet.  Each sense of a word is in a different 
+<B>synset </B>. </DD>
+
+<DT><B>sense key</B>  </DT>
+<DD>Information necessary to find a sense in the WordNet 
+database.  A sense key combines a <B>lemma </B> field and codes for the synset 
+type, lexicographer id, lexicographer file number, and information about 
+a satellite's <B>head synset </B>, if required.  See <B><A HREF="senseidx.5WN.html">senseidx</B>(5WN)</A>
+ for a description 
+of the format of a sense key. </DD>
+
+<DT><B>subordinate</B>  </DT>
+<DD>Same as <B>hyponym </B>. </DD>
+
+<DT><B>superordinate</B> 
+ </DT>
+<DD>Same as <B>hypernym </B>. </DD>
+
+<DT><B>synset</B>  </DT>
+<DD>A synonym set; a set of words that are interchangeable 
+in some context without changing the truth value of the preposition in 
+which they are embedded. </DD>
+
+<DT><B>troponym</B>  </DT>
+<DD>A verb expressing a specific manner 
+elaboration of another verb. <B>X </B> is a troponym of <B>Y </B> if <B>to X </B> is <B>to Y </B> in 
+some manner. </DD>
+
+<DT><B>unique beginner</B>  </DT>
+<DD>A noun synset with no <B>superordinate </B>. </DD>
+</DL>
+<P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">DESCRIPTION</A></LI>
+<UL>
+<LI><A NAME="toc2" HREF="#sect2">System Description</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">Database Organization</A></LI>
+</UL>
+<LI><A NAME="toc4" HREF="#sect4">GLOSSARY OF TERMS</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wngroups.7WN.html

@@ -0,0 +1,80 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WNGROUPS(7WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+wngroups - discussion of WordNet search code to group similar verb 
+senses  
+<H2><A NAME="sect1" HREF="#toc1">DESCRIPTION </A></H2>
+Some similar senses of verbs have been grouped by 
+the lexicographers. This grouping is done statically in the lexicographer 
+source files using the semantic <I>pointer_symbol </I> <B>$ </B>. Transitivity is used 
+to combine groups of overlapping senses into the largest sense groups 
+possible.  
+<H2><A NAME="sect2" HREF="#toc2">NOTES </A></H2>
+Coverage of verb groups is incomplete.  
+<H2><A NAME="sect3" HREF="#toc3">ENVIRONMENT VARIABLES 
+(UNIX) </A></H2>
+
+<DL>
+
+<DT><B>WNHOME</B>  </DT>
+<DD>Base directory for WordNet.  Default is <B>/usr/local/WordNet-3.0 
+</B>. </DD>
+
+<DT><B>WNSEARCHDIR</B>  </DT>
+<DD>Directory in which the WordNet database has been installed. 
+  Default is <B>WNHOME/dict </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect4" HREF="#toc4">REGISTRY (WINDOWS) </A></H2>
+
+<DL>
+
+<DT><B>HKEY_LOCAL_MACHINE\SOFTWARE\WordNet\3.0\WNHome</B> 
+ </DT>
+<DD>Base directory for WordNet.  Default is <B>C:\Program&nbsp;Files\WordNet\3.0 </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect5" HREF="#toc5">FILES 
+</A></H2>
+
+<DL>
+
+<DT><B>sentidx.vrb</B>  </DT>
+<DD>verb sense keys and sentence frame numbers </DD>
+
+<DT><B>sents.vrb</B>  </DT>
+<DD>example 
+sentence frames </DD>
+</DL>
+ 
+<H2><A NAME="sect6" HREF="#toc6">SEE ALSO </A></H2>
+<B><A HREF="wn.1WN.html">wn</B>(1WN)</A>
+, <B><A HREF="wnb.1WN.html">wnb</B>(1WN)</A>
+, <B><A HREF="senseidx.5WN.html">senseidx</B>(5WN)</A>
+, <B><A HREF="wnsearch.3WN.html">wnsearch</B>(3WN)</A>
+, 
+<B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+, <B><A HREF="wnintro.7WN.html">wnintro</B>(7WN)</A>
+. <P>
+ <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">DESCRIPTION</A></LI>
+<LI><A NAME="toc2" HREF="#sect2">NOTES</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">ENVIRONMENT VARIABLES (UNIX)</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">REGISTRY (WINDOWS)</A></LI>
+<LI><A NAME="toc5" HREF="#sect5">FILES</A></LI>
+<LI><A NAME="toc6" HREF="#sect6">SEE ALSO</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wninput.5WN.html

@@ -0,0 +1,491 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WNINPUT(5WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+noun.<I>suffix </I>, verb.<I>suffix </I>, adj.<I>suffix </I>, adv.<I>suffix </I> - WordNet lexicographer 
+files that are input to  <B><A HREF="grind.1WN.html">grind</B>(1WN)</A>
+  
+<H2><A NAME="sect1" HREF="#toc1">DESCRIPTION </A></H2>
+WordNet's source files 
+are written by lexicographers.  They are the product of a detailed relational 
+analysis of lexical semantics: a variety of lexical and semantic relations 
+are used to represent the organization of lexical knowledge.  Two kinds 
+of building blocks are distinguished in the source files: word forms and 
+word meanings.  Word forms are represented in their familiar orthography; 
+word meanings are represented by synonym sets (<I>synset </I>s) - lists of synonymous 
+word forms that are interchangeable in some context.  Two kinds of relations 
+are recognized: lexical and semantic.  Lexical relations hold between word 
+forms; semantic relations hold between word meanings. <P>
+ Lexicographer files 
+correspond to the syntactic categories implemented in WordNet - noun, verb, 
+adjective and adverb.  All of the synsets in a lexicographer file are in 
+the same syntactic category.  Each synset consists of a list of synonymous 
+words or collocations (eg. <B>"fountain pen" </B>, <B>"take in" </B>), and pointers that 
+describe the relations between this synset and other synsets.  These relations 
+include (but are not limited to) hypernymy/hyponymy, antonymy, entailment, 
+and meronymy/holonymy.  A word or collocation may appear in more than one 
+synset, and in more than one part of speech.  Each use of a word in a synset 
+represents a sense of that word in the part of speech corresponding to 
+the synset. <P>
+ Adjectives may be organized into clusters containing head 
+synsets and satellite synsets.  Adverbs generally point to the adjectives 
+from which they are derived. <P>
+ See  <B><A HREF="wngloss.7WN.html">wngloss</B>(7WN)</A>
+ for a glossary of WordNet 
+terminology and a discussion of the database's content and logical organization. 
+ 
+<H3><A NAME="sect2" HREF="#toc2">Lexicographer File Names </A></H3>
+The names of the lexicographer files are of 
+the form: <P>
+  <blockquote><I>pos</I>.<I>suffix</I>  </blockquote>
+<P>
+ where <I>pos </I> is either <B>noun </B>, <B>verb </B>, <B>adj </B> or <B>adv 
+</B>.  <I>suffix </I> may be used to organize groups of synsets into different files, 
+for example <B>noun.animal </B> and <B>noun.plant </B>.  See <B><A HREF="lexnames.5WN.html">lexnames</B>(5WN)</A>
+ for a list of 
+lexicographer file names that are used in building WordNet.  
+<H3><A NAME="sect3" HREF="#toc3">Pointers </A></H3>
+Pointers 
+are used to represent the relations between the words in one synset and 
+another.  Semantic pointers represent relations between word meanings, 
+and therefore pertain to all of the words in the source and target synsets. 
+ Lexical pointers represent relations between word forms, and pertain 
+only to specific words in the source and target synsets.  The following 
+pointer types are usually used to indicate lexical relations: Antonym, 
+Pertainym, Participle, Also See, Derivationally Related.  The remaining 
+pointer types are generally used to represent semantic relations. <P>
+ A relation 
+from a source to a target synset is formed by specifying a word from the 
+target synset in the source synset, followed by the <I>pointer_symbol </I> indicating 
+the pointer type.  The location of a pointer within a synset defines it 
+as either lexical or semantic.   The <FONT SIZE=-1><B>Lexicographer File Format </B></FONT>
+  section 
+describes the syntax for entering a semantic pointer, and <FONT SIZE=-1><B>Word Syntax 
+</B></FONT>
+  describes the syntax for entering a lexical pointer. <P>
+ Although there 
+are many pointer types, only certain types of relations are permitted 
+between synsets of each syntactic category. <P>
+ The <I>pointer_symbol </I>s for nouns 
+are:  <blockquote><B>! </B> <tt> </tt>&nbsp;<tt> </tt>&nbsp;Antonym <BR>
+ <B>@ </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Hypernym <BR>
+ <B>@i </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Instance Hypernym <BR>
+ <B>&nbsp; </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Hyponym <BR>
+ <B>&nbsp;i </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Instance 
+Hyponym <BR>
+ <B>#m </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Member holonym <BR>
+ <B>#s </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Substance holonym <BR>
+ <B>#p </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Part holonym <BR>
+ <B>%m 
+</B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Member meronym <BR>
+ <B>%s </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Substance meronym <BR>
+ <B>%p </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Part meronym <BR>
+ <B>= </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Attribute <BR>
+ <B>+ 
+</B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Derivationally related form<tt> </tt>&nbsp;<tt> </tt>&nbsp;<tt> </tt>&nbsp;<tt> </tt>&nbsp; <BR>
+ <B>;c </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Domain of synset - TOPIC <BR>
+ <B>-c </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Member of this 
+domain - TOPIC <BR>
+ <B>;r </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Domain of synset - REGION <BR>
+ <B>-r </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Member of this domain - REGION 
+<BR>
+ <B>;u </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Domain of synset - USAGE <BR>
+ <B>-u </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Member of this domain - USAGE <BR>
+  </blockquote>
+<P>
+ The <I>pointer_symbol 
+</I>s for verbs are:  <blockquote><B>! </B> <tt> </tt>&nbsp;<tt> </tt>&nbsp;Antonym <BR>
+ <B>@ </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Hypernym <BR>
+ <B>&nbsp; </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Hyponym <BR>
+ <B>* </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Entailment <BR>
+ <B>&gt; </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Cause 
+<BR>
+ <B>^ </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Also see <BR>
+ <B>$ </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Verb Group <BR>
+ <B>+ </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Derivationally related form<tt> </tt>&nbsp;<tt> </tt>&nbsp;<tt> </tt>&nbsp;<tt> </tt>&nbsp; <BR>
+ <B>;c </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Domain of 
+synset - TOPIC <BR>
+ <B>;r </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Domain of synset - REGION <BR>
+ <B>;u </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Domain of synset - USAGE 
+<BR>
+  </blockquote>
+<P>
+ The <I>pointer_symbol </I>s for adjectives are:  <blockquote><B>! </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Antonym <BR>
+ <B>&amp; </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Similar to <BR>
+ <B>&lt; 
+</B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Participle of verb <BR>
+ <B>\ </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Pertainym (pertains to noun) <BR>
+ <B>= </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Attribute <BR>
+ <B>^ </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Also 
+see <BR>
+ <B>;c </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Domain of synset - TOPIC <BR>
+ <B>;r </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Domain of synset - REGION <BR>
+ <B>;u </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Domain 
+of synset - USAGE <BR>
+  </blockquote>
+<P>
+ The <I>pointer_symbol </I>s for adverbs are:  <blockquote><B>! </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Antonym <BR>
+ 
+<B>\ </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Derived from adjective <BR>
+ <B>;c </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Domain of synset - TOPIC <BR>
+ <B>;r </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Domain of synset 
+- REGION <BR>
+ <B>;u </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;Domain of synset - USAGE <BR>
+  </blockquote>
+<P>
+ Many pointer types are reflexive, 
+meaning that if a synset contains a pointer to another synset, the other 
+synset should contain a corresponding reflexive pointer.   <B><A HREF="grind.1WN.html">grind</B>(1WN)</A>
+ automatically 
+inserts missing reflexive pointers for the following pointer types: <P>
+  
+<TABLE BORDER=0>
+ <TR> <TD ALIGN=CENTER><B>Pointer </B> </TD> <TD ALIGN=CENTER><B>Reflect </B> </TD> </TR>
+ <TR>  <TR> <TD ALIGN=LEFT>Antonym </TD> <TD ALIGN=LEFT>Antonym </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Hyponym </TD> <TD ALIGN=LEFT>Hypernym </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Hypernym 
+</TD> <TD ALIGN=LEFT>Hyponym </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Instance Hyponym </TD> <TD ALIGN=LEFT>Instance Hypernym </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Instance Hypernym </TD> 
+<TD ALIGN=LEFT>Instance Hyponym </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Holonym </TD> <TD ALIGN=LEFT>Meronym </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Meronym </TD> <TD ALIGN=LEFT>Holonym </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Similar to 
+</TD> <TD ALIGN=LEFT>Similar to </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Attribute </TD> <TD ALIGN=LEFT>Attribute </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Verb Group </TD> <TD ALIGN=LEFT>Verb Group </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Derivationally 
+Related </TD> <TD ALIGN=LEFT>Derivationally Related </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Domain of synset </TD> <TD ALIGN=LEFT>Member of Doman </TD> 
+</TR>
+ </TABLE>
+ 
+<H3><A NAME="sect4" HREF="#toc4">Verb Frames </A></H3>
+Each verb synset contains a list of generic sentence frames 
+illustrating the types of simple sentences in which the verbs in the synset 
+can be used.  For some verb senses, example sentences illustrating actual 
+uses of the verb are provided.  (See <FONT SIZE=-1><B>Verb Example Sentences </B></FONT>
+  in <B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+.) 
+Whenever there is no example sentence, the generic sentence frames specified 
+by the lexicographer are used.  The generic sentence frames are entered 
+in a synset as a comma-separated list of integer frame numbers.  The following 
+list is the text of the generic frames, preceded by their frame numbers: 
+<P>
+  <blockquote>1<tt> </tt>&nbsp;<tt> </tt>&nbsp;Something ----s <BR>
+ 2<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s <BR>
+ 3<tt> </tt>&nbsp;<tt> </tt>&nbsp;It is ----ing <BR>
+ 4<tt> </tt>&nbsp;<tt> </tt>&nbsp;Something is ----ing PP <BR>
+ 5<tt> </tt>&nbsp;<tt> </tt>&nbsp;Something 
+----s something Adjective/Noun <BR>
+ 6<tt> </tt>&nbsp;<tt> </tt>&nbsp;Something ----s Adjective/Noun <BR>
+ 7<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s Adjective 
+<BR>
+ 8<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s something <BR>
+ 9<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s somebody <BR>
+ 10<tt> </tt>&nbsp;<tt> </tt>&nbsp;Something ----s somebody <BR>
+ 
+11<tt> </tt>&nbsp;<tt> </tt>&nbsp;Something ----s something <BR>
+ 12<tt> </tt>&nbsp;<tt> </tt>&nbsp;Something ----s to somebody <BR>
+ 13<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s on something 
+<BR>
+ 14<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s somebody something <BR>
+ 15<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s something to somebody <BR>
+ 
+16<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s something from somebody <BR>
+ 17<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s somebody with something 
+<BR>
+ 18<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s somebody of something <BR>
+ 19<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s something on somebody 
+<BR>
+ 20<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s somebody PP <BR>
+ 21<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s something PP <BR>
+ 22<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s PP 
+<BR>
+ 23<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody's (body part) ----s <BR>
+ 24<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s somebody to INFINITIVE <BR>
+ 25<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody 
+----s somebody INFINITIVE <BR>
+ 26<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s that CLAUSE <BR>
+ 27<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s to somebody 
+<BR>
+ 28<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s to INFINITIVE <BR>
+ 29<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s whether INFINITIVE <BR>
+ 30<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody 
+----s somebody into V-ing something <BR>
+ 31<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s something with something 
+<BR>
+ 32<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s INFINITIVE <BR>
+ 33<tt> </tt>&nbsp;<tt> </tt>&nbsp;Somebody ----s VERB-ing <BR>
+ 34<tt> </tt>&nbsp;<tt> </tt>&nbsp;It ----s that CLAUSE <BR>
+ 35<tt> </tt>&nbsp;<tt> </tt>&nbsp;Something 
+----s INFINITIVE <BR>
+  </blockquote>
+ 
+<H3><A NAME="sect5" HREF="#toc5">Lexicographer File Format </A></H3>
+Synsets are entered one per 
+line, and each line is terminated with a newline character.  A line containing 
+a synset may be as long as necessary, but no newlines can be entered within 
+a synset.  Within a synset, spaces or tabs may be used to separate entities. 
+ Items enclosed in italicized square brackets may not be present. <P>
+ The 
+general synset syntax is: <P>
+  <blockquote><B>{ </B> <I>&nbsp;&nbsp;words&nbsp;&nbsp;pointers&nbsp;&nbsp; </I> <B>( </B> <I>&nbsp;gloss&nbsp; </I> <B>)&nbsp;&nbsp;} </B> 
+<BR>
+  </blockquote>
+<P>
+ Synsets of this form are valid for all syntactic categories except 
+verb, and are referred to as basic synsets.  At least one <I>word </I> and a <I>gloss 
+</I> are required to form a valid synset.  Pointers entered following all the 
+<I>words </I> in a synset represent semantic relations between all the words 
+in the source and target synsets. <P>
+ For verbs, the basic synset syntax is 
+defined as follows: <P>
+   <blockquote><B>{ </B> <I>&nbsp;&nbsp;words&nbsp;&nbsp;pointers&nbsp;&nbsp;frames&nbsp;&nbsp; </I> <B>( </B> &nbsp;<I>gloss&nbsp; </I> <B>)&nbsp;&nbsp;} 
+</B> <BR>
+  </blockquote>
+<P>
+ Adjective may be organized into clusters containing one or more head 
+synsets and optional satellite synsets.  Adjective clusters are of the 
+form: <P>
+  <blockquote><B>[ </B><BR>
+ <I>head synset </I><BR>
+ [satellite synsets] <BR>
+ [-] <BR>
+ [additional head/satellite 
+synsets] <BR>
+ <B>] </B> <BR>
+  </blockquote>
+ <P>
+ Each adjective cluster is enclosed in square brackets, 
+and may have one or more parts.  Each part consists of a head synset and 
+optional satellite synsets that are conceptually similar to the head synset's 
+meaning.  Parts of a cluster are separated by one or more hyphens (<B>- </B>) on 
+a line by themselves, with the terminating square bracket following the 
+last synset.  Head and satellite synsets follow the syntax of basic synsets, 
+however a "Similar to" pointer must be specified in a head synset for 
+each of its satellite synsets.  Most adjective clusters contain two antonymous 
+parts.  See <B><A HREF="wngloss.7WN.html">wngloss</B>(7WN)</A>
+ for a discussion of adjective clusters, and <FONT SIZE=-1><B>Special 
+Adjective Syntax </B></FONT>
+  for more information on adjective cluster syntax. <P>
+ Synsets 
+for relational adjectives (pertainyms) and participial adjectives do not 
+adhere to the cluster structure.  They use the basic synset syntax. <P>
+ Comments 
+can be entered in a lexicographer file by enclosing the text of the comment 
+in parentheses.  Note that comments <B>cannot </B> appear within a synset, as 
+parentheses within a synset have an entirely different meaning (see <FONT SIZE=-1><B>Gloss 
+Syntax </B></FONT>
+  ).  However, entire synsets (or adjective clusters) can be "commented 
+out" by enclosing them in parentheses.  This is often used by the lexicographers 
+to verify the syntax of files under development or to leave a note to 
+oneself while working on entries.  
+<H3><A NAME="sect6" HREF="#toc6">Word Syntax </A></H3>
+A synset must have at least 
+one word, and the words of a synset must appear after the opening brace 
+and before any other synset constructs. A word may be entered in either 
+the simple word or word/pointer syntax. <P>
+ A simple word is of the form: 
+<P>
+  <blockquote><I>word[ </I> <B>( </B> <I>marker </I> <B>) </B> <I>][lex_id] </I> <B>, </B> <BR>
+  </blockquote>
+<P>
+ <I>word </I> may be entered in any combination 
+of upper and lower case unless it is in an adjective cluster.  A collocation 
+is entered by joining the individual words with an underscore character 
+(<B>_ </B>). Numbers (integer or real) may be entered, either by themselves or 
+as part of a word string, by following the number with a double quote 
+(<B>" </B>). <P>
+ See  <FONT SIZE=-1><B>Special Adjective Syntax </B></FONT>
+  for a description of adjective clusters 
+and markers. <P>
+ <I>word </I> may be followed by an integer <I>lex_id </I> from <B>1 </B> to <B>15 
+</B>.  The <I>lex_id </I> is used to distinguish different senses of the same word 
+within a lexicographer file.  The lexicographer assigns <I>lex_id </I> values, 
+usually in ascending order, although there is no requirement that the 
+numbers be consecutive.  The default is <B>0 </B>, and does not have to be specified. 
+ A <I>lex_id </I> must be used on pointers if the desired sense has a non-zero 
+<I>lex_id </I> in its synset specification. <P>
+ Word/pointer syntax is of the form: 
+<P>
+  <blockquote><B>[&nbsp;&nbsp; </B> <I>word[ </I> <B>( </B> <I>marker </I> <B>) </B> <I>][lex_id] </I> <B>, </B> <I>&nbsp;&nbsp;pointers&nbsp;&nbsp; </I> <B>] </B> <BR>
+  </blockquote>
+<P>
+ This syntax 
+is used when one or more pointers correspond only to the specific word 
+in the word/pointer set, rather than all the words in the synset, and 
+represents a lexical relation.  Note that a word/pointer set appears within 
+a synset, therefore the square brackets used to enclose it are treated 
+differently from those used to define an adjective cluster.  Only one word 
+can be specified in each word/pointer set, and any number of pointers 
+may be included.  A synset can have any number of word/pointer sets.  Each 
+is treated by <B><A HREF="grind.1WN.html">grind</B>(1WN)<B></B></A>
+ essentially as a <I>word </I>, so they all must appear 
+before any synset <I>pointers </I> representing semantic relations. <P>
+ For verbs, 
+the word/pointer syntax is extended in the following manner to allow the 
+user to specify generic sentence frames that, like pointers, correspond 
+only to a specific word, rather than all the words in the synset.  In this 
+case, <I>pointers </I> are optional. <P>
+  <blockquote><B>[&nbsp;&nbsp; </B> <I>word </I> <B>, </B> &nbsp;&nbsp;<I>[pointers]&nbsp;&nbsp;frames&nbsp;&nbsp; </I> <B>] 
+</B> <BR>
+  </blockquote>
+ 
+<H3><A NAME="sect7" HREF="#toc7">Pointer Syntax </A></H3>
+Pointers are optional in synsets.  If a pointer is specified 
+outside of a word/pointer set, the relation is applied to all of the words 
+in the synset, including any words specified using the word/pointer syntax. 
+ This indicates a semantic relation between the meanings of the words 
+in the synsets.  If specified within a word/pointer set, the relation corresponds 
+only to the word in the set and represents a lexical relation. <P>
+ A pointer 
+is of the form: <P>
+  <blockquote><I>[lex_filename </I><B>: </B> <I>]word[lex_id] </I><B>, </B><I>pointer_symbol </I> <BR>
+  </blockquote>
+<P>
+ 
+or: <P>
+  <blockquote><I>[lex_filename </I><B>: </B> <I>]word[lex_id] </I><B>^ </B><I>word[lex_id] </I><B>, </B><I>pointer_symbol </I> <BR>
+ 
+ </blockquote>
+<P>
+ For pointers, <I>word </I> indicates a word in another synset.  When the second 
+form of a pointer is used, the first <I>word </I> indicates a word in a head 
+synset, and the second is a word in a satellite of that cluster.  <I>word 
+</I> may be followed by a <I>lex_id </I> that is used to match the pointer to the 
+correct target synset.  The synset containing <I>word </I> may reside in another 
+lexicographer file.  In this case, <I>word </I> is preceded by <I>lex_filename </I> as 
+shown. <P>
+ See <FONT SIZE=-1><B>Pointers </B></FONT>
+  for a list of <I>pointer_symbol </I>s and their meanings. 
+ 
+<H3><A NAME="sect8" HREF="#toc8">Verb Frame List Syntax </A></H3>
+Frame numbers corresponding to generic sentence 
+frames must be entered in each verb synset.  If a frame list is specified 
+outside of a word/pointer set, the verb frames in the list apply to all 
+of the words in the synset, including any words specified using the word/pointer 
+syntax.  If specified within a word/pointer set, the verb frames in the 
+list correspond only to the word in the set. <P>
+ A frame number list is entered 
+as follows: <P>
+  <blockquote><B>frames: </B>&nbsp;&nbsp;<I>f_num </I>[<B>, </B><I>f_num...] </I>  </blockquote>
+<P>
+ Where <I>f_num </I> specifies a generic 
+frame number. See <FONT SIZE=-1><B>Verb Frames </B></FONT>
+  for a list of generic sentences and their 
+corresponding frame numbers.  
+<H3><A NAME="sect9" HREF="#toc9">Gloss Syntax </A></H3>
+A gloss is included in all synsets. 
+ The lexicographer may enter a text string of any length desired.  A gloss 
+is simply a string enclosed in parentheses with no embedded carriage returns. 
+ It provides a definition of what the synset represents and/or example 
+sentences.  
+<H3><A NAME="sect10" HREF="#toc10">Special Adjective Syntax </A></H3>
+The syntax for representing antonymous 
+adjective synsets requires several additional conditions. <P>
+ The first word 
+of a head synset <B>must </B> be entered in upper case, and can be thought of 
+as the head word of the head synset.  The <I>word </I> part of a pointer from 
+one head synset to another head synset within the same cluster (usually 
+an antonym) must also be entered in upper case.  Usually antonymous adjectives 
+are entered using the word/pointer syntax described in <FONT SIZE=-1><B>Word Syntax </B></FONT>
+  to 
+indicate a lexical relation.  There is no restriction on the number of 
+parts that a cluster may have, and some clusters have three parts, representing 
+antonymous triplets, such as <B>solid </B>, <B>liquid </B>, and <B>gas </B>. <P>
+ A cross-cluster 
+pointer may be specified, allowing a head or satellite synset to point 
+to a head synset in a different cluster.  A cross-cluster pointer is indicated 
+by entering the <I>word </I> part of the pointer in upper case. <P>
+ An adjective 
+may be annotated with a syntactic marker indicating a limitation on the 
+syntactic position the adjective may have in relation to noun that it 
+modifies.  If so marked, the marker appears between the word and its following 
+comma.  If a <I>lex_id </I> is specified, the marker immediately follows it.  The 
+syntactic markers are:  <blockquote><B>(p) </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;predicate position <BR>
+ <B>(a) </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;prenominal (attributive) 
+position <BR>
+ <B>(ip) </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;immediately postnominal position<tt> </tt>&nbsp;<tt> </tt>&nbsp;<tt> </tt>&nbsp;<tt> </tt>&nbsp; <BR>
+  </blockquote>
+ 
+<H2><A NAME="sect11" HREF="#toc11">EXAMPLES </A></H2>
+<I>(Note that 
+these are hypothetical examples not found in the WordNet lexicographer 
+files.) </I> <P>
+ Sample noun synsets:  <blockquote>{ canine, [ dog1, cat,! ] pooch, canid,@ 
+} <BR>
+ { collie, dog1,@ (large multi-colored dog with pointy nose) } <BR>
+ { hound, 
+hunting_dog, pack,#m dog1,@ } <BR>
+ { dog, } <BR>
+  </blockquote>
+<P>
+ Sample verb synsets:  <blockquote>{ [ confuse, 
+clarify,! frames: 1 ] blur, obscure, frames: 8, 10 } <BR>
+ { [ clarify, confuse,! 
+] make_clear, interpret,@ frames: 8 } <BR>
+ { interpret, construe, understand,@ 
+frames: 8 } <BR>
+  </blockquote>
+<P>
+ Sample adjective clusters:  <blockquote>[ <BR>
+ { [ HOT, COLD,! ] lukewarm(a), 
+TEPID,^ (hot to the touch) } <BR>
+ { warm, } <BR>
+ - <BR>
+ { [ COLD, HOT,! ] frigid, (cold 
+to the touch) } <BR>
+ { freezing, } <BR>
+ ] <BR>
+  </blockquote>
+<P>
+ Sample adverb synsets:  <blockquote>{ [ basically, 
+adj.all:essential^basic,\ ] [ essentially, adj.all:basic^fundamental,\ ] ( by 
+one's very nature )} <BR>
+ { pointedly, adj.all:pungent^pointed,\ } <BR>
+ { [ badly, 
+adj.all:bad,\ well,! ] ill, ("He was badly prepared") } <BR>
+  </blockquote>
+ 
+<H2><A NAME="sect12" HREF="#toc12">SEE ALSO </A></H2>
+<B><A HREF="grind.1WN.html">grind</B>(1WN)</A>
+, 
+<B><A HREF="wnintro.5WN.html">wnintro</B>(5WN)</A>
+, <B><A HREF="lexnames.5WN.html">lexnames</B>(5WN)</A>
+, <B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+, <B><A HREF="uniqbeg.7WN.html">uniqbeg</B>(7WN)</A>
+, <B><A HREF="wngloss.7WN.html">wngloss</B>(7WN)</A>
+. <P>
+Fellbaum, 
+C. (1998), ed. <I>"WordNet: An Electronic Lexical Database" </I>. MIT Press, Cambridge, 
+MA. <P>
+ <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">DESCRIPTION</A></LI>
+<UL>
+<LI><A NAME="toc2" HREF="#sect2">Lexicographer File Names</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">Pointers</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">Verb Frames</A></LI>
+<LI><A NAME="toc5" HREF="#sect5">Lexicographer File Format</A></LI>
+<LI><A NAME="toc6" HREF="#sect6">Word Syntax</A></LI>
+<LI><A NAME="toc7" HREF="#sect7">Pointer Syntax</A></LI>
+<LI><A NAME="toc8" HREF="#sect8">Verb Frame List Syntax</A></LI>
+<LI><A NAME="toc9" HREF="#sect9">Gloss Syntax</A></LI>
+<LI><A NAME="toc10" HREF="#sect10">Special Adjective Syntax</A></LI>
+</UL>
+<LI><A NAME="toc11" HREF="#sect11">EXAMPLES</A></LI>
+<LI><A NAME="toc12" HREF="#sect12">SEE ALSO</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wnintro.1WN.html

@@ -0,0 +1,81 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WNINTRO(1WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+wnintro - WordNet user commands  
+<H2><A NAME="sect1" HREF="#toc1">SYNOPSIS </A></H2>
+<P>
+<B>wn </B> - command line interface 
+to WordNet database <P>
+<B>wnb </B> - window based WordNet browser  
+<H2><A NAME="sect2" HREF="#toc2">DESCRIPTION </A></H2>
+This 
+section of the <I>WordNet Reference Manual </I> contains manual pages that describe 
+commands available with the various WordNet system packages. <P>
+ The WordNet 
+interfaces  <B><A HREF="wn.1WN.html">wn</B>(1WN)</A>
+ and <B><A HREF="wnb.1WN.html">wnb</B>(1WN)</A>
+ allow the user to search the WordNet 
+database and display the information textually.    
+<H2><A NAME="sect3" HREF="#toc3">ENVIRONMENT VARIABLES 
+(UNIX) </A></H2>
+
+<DL>
+
+<DT><B>WNHOME</B>  </DT>
+<DD>Base directory for WordNet.  Default is <B>/usr/local/WordNet-3.0 
+</B>. </DD>
+
+<DT><B>WNSEARCHDIR</B>  </DT>
+<DD>Directory in which the WordNet database has been installed. 
+  Default is <B>WNHOME/dict </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect4" HREF="#toc4">REGISTRY (WINDOWS) </A></H2>
+
+<DL>
+
+<DT><B>HKEY_LOCAL_MACHINE\SOFTWARE\WordNet\3.0\WNHome</B> 
+ </DT>
+<DD>Base directory for WordNet.  Default is <B>C:\Program&nbsp;Files\WordNet\3.0 </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect5" HREF="#toc5">SEE 
+ALSO </A></H2>
+<B><A HREF="grind.1WN.html">grind</B>(1WN)</A>
+, <B><A HREF="wn.1WN.html">wn</B>(1WN)</A>
+, <B><A HREF="wnb.1WN.html">wnb</B>(1WN)</A>
+, <B><A HREF="wnintro.3WN.html">wnintro</B>(3WN)</A>
+, <B><A HREF="wnintro.5WN.html">wnintro</B>(5WN)</A>
+, <B><A HREF="wnintro.7WN.html">wnintro</B>(7WN)</A>
+. 
+<P>
+Fellbaum, C. (1998), ed. <I>"WordNet: An Electronic Lexical Database" </I>. MIT 
+Press, Cambridge, MA.  
+<H2><A NAME="sect6" HREF="#toc6">AVAILABILITY </A></H2>
+WordNet has a World Wide Web site at 
+<B><A HREF="http://wordnet.princeton.edu">http://wordnet.princeton.edu</A>
+ </B>.  From this web site users can learn about 
+the WordNet project, run several different interfaces to the WordNet database, 
+and download various WordNet system packages and <I>"Five Papers on WordNet" 
+</I>. <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">SYNOPSIS</A></LI>
+<LI><A NAME="toc2" HREF="#sect2">DESCRIPTION</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">ENVIRONMENT VARIABLES (UNIX)</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">REGISTRY (WINDOWS)</A></LI>
+<LI><A NAME="toc5" HREF="#sect5">SEE ALSO</A></LI>
+<LI><A NAME="toc6" HREF="#sect6">AVAILABILITY</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wnintro.3WN.html

@@ -0,0 +1,365 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WNINTRO(3WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+wnintro - introduction to WordNet library functions  
+<H2><A NAME="sect1" HREF="#toc1">DESCRIPTION 
+</A></H2>
+This section of the <I>WordNet Reference Manual </I> contains manual pages that 
+describe the WordNet library functions and API. <P>
+ Functions are organized 
+into the following categories:  <P>
+  <TABLE BORDER=0>
+ <TR> <TD ALIGN=LEFT><B>Category </B> </TD> <TD ALIGN=LEFT><B>Manual Page </B> </TD> <TD ALIGN=LEFT><B>Object File 
+</B> </TD> </TR>
+ <TR>  <TR> <TD ALIGN=LEFT>Database Search </TD> <TD ALIGN=LEFT>wnsearch (3WN) </TD> <TD ALIGN=LEFT>search.o </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Morphology </TD> <TD ALIGN=LEFT>morph (3WN) 
+</TD> <TD ALIGN=LEFT>morph.o </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Misc. Utility </TD> <TD ALIGN=LEFT>wnutil (3WN) </TD> <TD ALIGN=LEFT>wnutil.o </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Binary Search </TD> <TD ALIGN=LEFT>binsrch 
+(3WN) </TD> <TD ALIGN=LEFT>binsrch.o </TD> </TR>
+ </TABLE>
+<P>
+ The WordNet library is used by all of the searching 
+interfaces provided with the various WordNet packages.  Additional programs 
+in the system, such as <B><A HREF="grind.1WN.html">grind</B>(1WN)</A>
+, also use functions in this library. 
+<P>
+ The WordNet library is provided in both source and binary forms (on some 
+platforms) to allow users to build applications and tools to their own 
+specifications that utilize the WordNet database.  We do not provide programming 
+support or assistance. <P>
+ The code conforms to ANSI C standards.  Functions 
+are defined with function prototypes.  If you do not have a compiler that 
+accepts prototypes, you must edit the source code and remove the prototypes 
+before compiling.  
+<H2><A NAME="sect2" HREF="#toc2">LIST OF WORDNET LIBRARY FUNCTIONS </A></H2>
+Not all library functions 
+are listed below. Missing are mainly functions that are called by documented 
+ones, or ones that were written for specific applications or tools used 
+during WordNet development.  Data structures are defined in <B>wn.h </B>. <P>
+  
+<H3><A NAME="sect3" HREF="#toc3">Database 
+Searching Functions (search.o) </A></H3>
+<P>
+ 
+<DL>
+
+<DT><B>findtheinfo </B>  </DT>
+<DD>Primary search function for 
+WordNet database.  Returns formatted search results in text buffer.  Used 
+by WordNet interfaces to perform requested search. </DD>
+
+<DT><B>findtheinfo_ds</B>  </DT>
+<DD>Primary 
+search function for WordNet database.  Returns search results in linked 
+list data structure. </DD>
+
+<DT><B>is_defined</B>  </DT>
+<DD>Set bit for each search type that is valid 
+for the search word passed and return bit mask. </DD>
+
+<DT><B>in_wn</B>  </DT>
+<DD>Set bit for each 
+syntactic category that search word is in. </DD>
+
+<DT><B>index_lookup</B>  </DT>
+<DD>Find word in index 
+file and return parsed entry in data structure. Input word must be exact 
+match of string in database.  Called by <B>getindex() </B>. </DD>
+
+<DT><B>getindex</B>  </DT>
+<DD>Find word 
+in index file, trying different techniques - replace hyphens with underscores, 
+replace underscores with hyphens, strip hyphens and underscores, strip 
+periods. </DD>
+
+<DT><B>read_synset</B>  </DT>
+<DD>Read synset from data file at byte offset passed 
+and return parsed entry in data structure.  Calls <B>parse_synset() </B>. </DD>
+
+<DT><B>parse_synset</B> 
+ </DT>
+<DD>Read synset at current byte offset in file and return parsed entry in 
+data structure. </DD>
+
+<DT><B>free_syns</B>  </DT>
+<DD>Free a synset linked list allocated by <B>findtheinfo_ds() 
+</B>. </DD>
+
+<DT><B>free_synset</B>  </DT>
+<DD>Free a synset structure. </DD>
+
+<DT><B>free_index</B>  </DT>
+<DD>Free an index structure. 
+</DD>
+
+<DT><B>traceptrs_ds</B>  </DT>
+<DD>Recursive search algorithm to trace a pointer tree and return 
+results in linked list. </DD>
+
+<DT><B>do_trace</B>  </DT>
+<DD>Do requested search on synset passed 
+returning formatted output in buffer. </DD>
+</DL>
+<P>
+  
+<H3><A NAME="sect4" HREF="#toc4">Morphology Functions (morph.o) </A></H3>
+<P>
+ 
+
+<DL>
+
+<DT><B>morphinit</B>  </DT>
+<DD>Open exception list files. </DD>
+
+<DT><B>re_morphinit</B>  </DT>
+<DD>Close exception list 
+files and reopen. </DD>
+
+<DT><B>morphstr</B>  </DT>
+<DD>Try to find base form (lemma) of word or collocation 
+in syntactic category passed.  Calls <B>morphword() </B> for each word in string 
+passed. </DD>
+
+<DT><B>morphword</B>  </DT>
+<DD>Try to find base form (lemma) of individual word in 
+syntactic category passed. </DD>
+</DL>
+<P>
+  
+<H3><A NAME="sect5" HREF="#toc5">Utility Functions (wnutil.o) </A></H3>
+<P>
+ 
+<DL>
+
+<DT><B>wninit</B>  </DT>
+<DD>Top level 
+function to open database files and morphology exception lists. </DD>
+
+<DT><B>re_wninit</B> 
+ </DT>
+<DD>Top level function to close and reopen database files and morphology 
+exception lists. </DD>
+
+<DT><B>cntwords</B>  </DT>
+<DD>Count the number of underscore or space separated 
+words in a string. </DD>
+
+<DT><B>strtolower</B>  </DT>
+<DD>Convert string to lower case and remove 
+trailing adjective marker if found. </DD>
+
+<DT><B>ToLowerCase</B>  </DT>
+<DD>Convert string passed 
+to lower case. </DD>
+
+<DT><B>strsubst</B>  </DT>
+<DD>Replace all occurrences of <I>from </I> with <I>to </I> in <I>str 
+</I>. </DD>
+
+<DT><B>getptrtype</B>  </DT>
+<DD>Return code for pointer type character passed. </DD>
+
+<DT><B>getpos</B>  </DT>
+<DD>Return 
+syntactic category code for string passed. </DD>
+
+<DT><B>getsstype</B>  </DT>
+<DD>Return synset type 
+code for string passed. </DD>
+
+<DT><B>FmtSynset</B>  </DT>
+<DD>Reconstruct synset string from synset 
+pointer. </DD>
+
+<DT><B>StrToPos</B>  </DT>
+<DD>Passed string for syntactic category, returns corresponding 
+integer value. </DD>
+
+<DT><B>GetSynsetForSense</B>  </DT>
+<DD>Return synset for sense key passed. </DD>
+
+<DT><B>GetDataOffset</B> 
+ </DT>
+<DD>Find synset offset for sense. </DD>
+
+<DT><B>GetPolyCount</B>  </DT>
+<DD>Find polysemy count for sense 
+passed. </DD>
+
+<DT><B>GetWORD</B>  </DT>
+<DD>Return word part of sense key. </DD>
+
+<DT><B>GetPOS</B>  </DT>
+<DD>Return syntactic 
+category code for sense key passed. </DD>
+
+<DT><B>WNSnsToStr</B>  </DT>
+<DD>Generate sense key for 
+index entry passed. </DD>
+
+<DT><B>GetValidIndexPointer</B>  </DT>
+<DD>Search for string and/or base 
+form of word in database and return index structure for word if found. 
+</DD>
+
+<DT><B>GetWNSense</B>  </DT>
+<DD>Return sense number in database for sense key. </DD>
+
+<DT><B>GetSenseIndex</B> 
+ </DT>
+<DD>Return parsed sense index entry for sense key passed. </DD>
+
+<DT><B>default_display_message</B> 
+ </DT>
+<DD>Default function to use as value of <B>display_message </B>.  Simply returns 
+<B>-1 </B>. </DD>
+</DL>
+<P>
+  
+<H3><A NAME="sect6" HREF="#toc6">Binary Search Functions (binsrch.o) </A></H3>
+<P>
+ 
+<DL>
+
+<DT><B>bin_search</B>  </DT>
+<DD>General purpose binary 
+search function to search for key as first item on line in sorted file. 
+</DD>
+
+<DT><B>copyfile</B>  </DT>
+<DD>Copy contents from one file to another. </DD>
+
+<DT><B>replace_line</B>  </DT>
+<DD>Replace 
+a line in a sorted file.  </DD>
+
+<DT><B>insert_line</B>  </DT>
+<DD>Insert a line into a sorted file. 
+</DD>
+</DL>
+ 
+<H2><A NAME="sect7" HREF="#toc7">HEADER FILE </A></H2>
+
+<DL>
+
+<DT><B>wn.h</B>  </DT>
+<DD>WordNet include file of constants, data structures, 
+external declarations for global variables initialized in <B>wnglobal.c </B>. Also 
+lists function prototypes for library API. It must be included to use any 
+WordNet library functions. </DD>
+</DL>
+ 
+<H2><A NAME="sect8" HREF="#toc8">NOTES </A></H2>
+All library functions that access the 
+database files expect the files to be open.  The function <B><A HREF="wninit.3WN.html">wninit</B>(3WN)</A>
+ must 
+be called before other database access functions such as <B><A HREF="findtheinfo.3WN.html">findtheinfo</B>(3WN)</A>
+ 
+or <B><A HREF="read_synset.3WN.html">read_synset</B>(3WN)</A>
+.<B></B> <P>
+ Inclusion of the header file <B>wn.h </B> is necessary. <P>
+ The 
+command line interface is a good example of a simple application that 
+uses several WordNet library functions.  <P>
+ Many of the library functions 
+are passed or return syntactic category or synset type information.  The 
+following table lists the possible categories as integer codes, synset 
+type constant names, syntactic category constant names, single characters 
+and character strings. <P>
+  <TABLE BORDER=0>
+ <TR> <TD ALIGN=CENTER><B>Integer </B> </TD> <TD ALIGN=CENTER><B>Synset Type </B> </TD> <TD ALIGN=CENTER><B>Syntactic Category </B> 
+</TD> <TD ALIGN=CENTER><B>Char </B> </TD> <TD ALIGN=CENTER><B>String </B>  </TD> </TR>
+ <TR>  <TR> <TD ALIGN=CENTER>1 </TD> <TD ALIGN=LEFT>NOUN </TD> <TD ALIGN=LEFT>NOUN </TD> <TD ALIGN=CENTER>n </TD> <TD ALIGN=LEFT>noun </TD> </TR>
+ <TR> <TD ALIGN=CENTER>2 </TD> <TD ALIGN=LEFT>VERB </TD> <TD ALIGN=LEFT>VERB </TD> <TD ALIGN=CENTER>v </TD> <TD ALIGN=LEFT>verb 
+</TD> </TR>
+ <TR> <TD ALIGN=CENTER>3 </TD> <TD ALIGN=LEFT>ADJ </TD> <TD ALIGN=LEFT>ADJ </TD> <TD ALIGN=CENTER>a </TD> <TD ALIGN=LEFT>adj </TD> </TR>
+ <TR> <TD ALIGN=CENTER>4 </TD> <TD ALIGN=LEFT>ADV </TD> <TD ALIGN=LEFT>ADV </TD> <TD ALIGN=CENTER>r </TD> <TD ALIGN=LEFT>adv </TD> </TR>
+ <TR> <TD ALIGN=CENTER>5 </TD> <TD ALIGN=LEFT>SATELLITE </TD> <TD ALIGN=LEFT>ADJ </TD> <TD ALIGN=CENTER>s 
+</TD> <TD ALIGN=LEFT><I>n/a </I> </TD> </TR>
+ </TABLE>
+ 
+<H2><A NAME="sect9" HREF="#toc9">ENVIRONMENT VARIABLES (UNIX) </A></H2>
+
+<DL>
+
+<DT><B>WNHOME</B>  </DT>
+<DD>Base directory for WordNet. 
+ Default is <B>/usr/local/WordNet-3.0 </B>. </DD>
+
+<DT><B>WNSEARCHDIR</B>  </DT>
+<DD>Directory in which the 
+WordNet database has been installed.   Default is <B>WNHOME/dict </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect10" HREF="#toc10">REGISTRY 
+(WINDOWS) </A></H2>
+
+<DL>
+
+<DT><B>HKEY_LOCAL_MACHINE\SOFTWARE\WordNet\3.0\WNHome</B>  </DT>
+<DD>Base directory for 
+WordNet.  Default is <B>C:\Program&nbsp;Files\WordNet\3.0 </B>. </DD>
+</DL>
+ 
+<H2><A NAME="sect11" HREF="#toc11">FILES </A></H2>
+
+<DL>
+
+<DT><B>lib/libwn.a</B>  </DT>
+<DD>WordNet 
+library (Unix) </DD>
+
+<DT><B>lib\wn.lib</B>  </DT>
+<DD>WordNet library (Windows) </DD>
+
+<DT><B>include</B>  </DT>
+<DD>header files 
+for use with WordNet library </DD>
+</DL>
+ 
+<H2><A NAME="sect12" HREF="#toc12">SEE ALSO </A></H2>
+<B><A HREF="wnintro.1WN.html">wnintro</B>(1WN)</A>
+, <B><A HREF="binsrch.3WN.html">binsrch</B>(3WN)</A>
+, <B><A HREF="morph.3WN.html">morph</B>(3WN)</A>
+, 
+<B><A HREF="wnsearch.3WN.html">wnsearch</B>(3WN)</A>
+, <B><A HREF="wnutil.3WN.html">wnutil</B>(3WN)</A>
+, <B><A HREF="wnintro.5WN.html">wnintro</B>(5WN)</A>
+, <B><A HREF="wnintro.7WN.html">wnintro</B>(7WN)</A>
+. <P>
+ Fellbaum, C. (1998), 
+ed. <I>"WordNet: An Electronic Lexical Database" </I>. MIT Press, Cambridge, MA. 
+ 
+<H2><A NAME="sect13" HREF="#toc13">BUGS </A></H2>
+Please report bugs to <B>wordnet@princeton.edu </B>. <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">DESCRIPTION</A></LI>
+<LI><A NAME="toc2" HREF="#sect2">LIST OF WORDNET LIBRARY FUNCTIONS</A></LI>
+<UL>
+<LI><A NAME="toc3" HREF="#sect3">Database Searching Functions (search.o)</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">Morphology Functions (morph.o)</A></LI>
+<LI><A NAME="toc5" HREF="#sect5">Utility Functions (wnutil.o)</A></LI>
+<LI><A NAME="toc6" HREF="#sect6">Binary Search Functions (binsrch.o)</A></LI>
+</UL>
+<LI><A NAME="toc7" HREF="#sect7">HEADER FILE</A></LI>
+<LI><A NAME="toc8" HREF="#sect8">NOTES</A></LI>
+<LI><A NAME="toc9" HREF="#sect9">ENVIRONMENT VARIABLES (UNIX)</A></LI>
+<LI><A NAME="toc10" HREF="#sect10">REGISTRY (WINDOWS)</A></LI>
+<LI><A NAME="toc11" HREF="#sect11">FILES</A></LI>
+<LI><A NAME="toc12" HREF="#sect12">SEE ALSO</A></LI>
+<LI><A NAME="toc13" HREF="#sect13">BUGS</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wnintro.5WN.html

@@ -0,0 +1,71 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WNINTRO(5WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+wnintro - introduction to descriptions of WordNet file formats  
+
+<H2><A NAME="sect1" HREF="#toc1">SYNOPSIS </A></H2>
+<P>
+<B>cntlist </B> - format of <B>cntlist </B> and <B>cntlist.rev </B> files <P>
+<B>lexnames </B> 
+- list of lexicographer file names and numbers <P>
+<B>prologdb </B> - description of 
+Prolog database files <P>
+<B>senseidx </B> - format of sense index file <P>
+<B>sensemap </B> 
+- mapping from senses in WordNet 2.1 to corresponding 3.0 senses <P>
+<B>wndb </B> - format 
+of WordNet database files  <P>
+<B>wninput </B> - format of WordNet lexicographer files 
+ 
+<H2><A NAME="sect2" HREF="#toc2">DESCRIPTION </A></H2>
+This section of the <I>WordNet Reference Manual </I> contains manual 
+pages that describe the formats of the various files included in different 
+WordNet 3.0 packages.  
+<H2><A NAME="sect3" HREF="#toc3">NOMENCLATURE </A></H2>
+All files are in ASCII.  Fields are generally 
+separated by one space, unless otherwise noted, and each line is terminated 
+with a newline character.  In the file format descriptions, terms in <I>italics 
+</I> refer to field names.  Characters or strings in <B>boldface </B> represent an 
+actual character or string as it appears in the file. Items enclosed in 
+italicized square brackets (<I>[&nbsp;&nbsp;] </I>) may not be present. Since several files 
+contain fields that have the identical meaning, field names are consistently 
+defined.  For example, several WordNet files contain one or more <I>synset_offset 
+</I> fields.  In each case, the definition of <I>synset_offset </I> is identical.  
+
+<H2><A NAME="sect4" HREF="#toc4">SEE ALSO </A></H2>
+<B><A HREF="wnintro.1WN.html">wnintro</B>(1WN)</A>
+, <B><A HREF="wnintro.3WN.html">wnintro</B>(3WN)</A>
+, <B><A HREF="cntlist.5WN.html">cntlist</B>(5WN)</A>
+, <B><A HREF="lexnames.5WN.html">lexnames</B>(5WN)</A>
+, <B><A HREF="prologdb.5WN.html">prologdb</B>(5WN)</A>
+, 
+<B><A HREF="senseidx.5WN.html">senseidx</B>(5WN)</A>
+, <B><A HREF="sensemap.5WN.html">sensemap</B>(5WN)</A>
+, <B><A HREF="wndb.5WN.html">wndb</B>(5WN)</A>
+, <B><A HREF="wninput.5WN.html">wninput</B>(5WN)</A>
+, <B><A HREF="wnintro.7WN.html">wnintro</B>(7WN)</A>
+, <B><A HREF="wngloss.7WN.html">wngloss</B>(7WN)</A>
+. 
+<P>
+Fellbaum, C. (1998), ed. <I>"WordNet: An Electronic Lexical Database" </I>. MIT 
+Press, Cambridge, MA. <P>
+ <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">SYNOPSIS</A></LI>
+<LI><A NAME="toc2" HREF="#sect2">DESCRIPTION</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">NOMENCLATURE</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">SEE ALSO</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wnintro.7WN.html

@@ -0,0 +1,57 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WNINTRO(7WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+wnintro - introduction to miscellaneous WordNet information  
+<H2><A NAME="sect1" HREF="#toc1">SYNOPSIS 
+</A></H2>
+<P>
+<B>morphy </B> - discussion of WordNet's morphological processing <P>
+<B>uniqbeg </B> - unique 
+beginners for noun hierarchies <P>
+<B>wngloss </B> - glossary of terms used in WordNet 
+<P>
+<B>wngroups </B> - discussion of WordNet search code to group similar senses <P>
+<B>wnlicens 
+</B> - text of WordNet license agreement <P>
+<B>wnpkgs </B> - information about WordNet 
+packages and distribution <P>
+<B>wnstats </B> - database statistics  
+<H2><A NAME="sect2" HREF="#toc2">DESCRIPTION </A></H2>
+This 
+section of the <I>WordNet Reference Manual </I> contains manual pages that describe 
+various topics related to WordNet and the semantic concordances, and a 
+glossary of terms.  
+<H2><A NAME="sect3" HREF="#toc3">SEE ALSO </A></H2>
+<B><A HREF="wnintro.1WN.html">wnintro</B>(1WN)</A>
+, <B><A HREF="wnintro.3WN.html">wnintro</B>(3WN)</A>
+, <B><A HREF="wnintro.5WN.html">wnintro</B>(5WN)</A>
+, 
+<B><A HREF="morphy.7WN.html">morphy</B>(7WN)</A>
+, <B><A HREF="uniqbeg.7WN.html">uniqbeg</B>(7WN)</A>
+, <B><A HREF="wngroups.7WN.html">wngroups</B>(7WN)</A>
+, <B><A HREF="wnlicens.7WN.html">wnlicens</B>(7WN)</A>
+, <B><A HREF="wnpkgs.7WN.html">wnpkgs</B>(7WN)</A>
+, 
+<B><A HREF="wnstats.7WN.html">wnstats</B>(7WN)</A>
+, <B><A HREF="wngloss.7WN.html">wngloss</B>(7WN)</A>
+. <P>
+Fellbaum, C. (1998), ed. <I>"WordNet: An Electronic 
+Lexical Database" </I>. MIT Press, Cambridge, MA. <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">SYNOPSIS</A></LI>
+<LI><A NAME="toc2" HREF="#sect2">DESCRIPTION</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">SEE ALSO</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wnlicens.7WN.html

@@ -0,0 +1,45 @@
+<!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WNLICENS(7WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+wnlicens - text of WordNet license  
+<H2><A NAME="sect1" HREF="#toc1">DESCRIPTION </A></H2>
+WordNet Release 3.0 
+<P>
+ This software and database is being provided to you, the LICENSEE, by 
+  Princeton University under the following license.  By obtaining, using 
+  and/or copying this software and database, you agree that you have  
+ read, understood, and will comply with these terms and conditions.:   
+   Permission to use, copy, modify and distribute this software and   
+database and its documentation for any purpose and without fee or   royalty 
+is hereby granted, provided that you agree to comply with   the following 
+copyright notice and statements, including the disclaimer,   and that 
+the same appear on ALL copies of the software, database and   documentation, 
+including modifications that you make for internal   use or for distribution. 
+     WordNet 3.0 Copyright 2006 by Princeton University.  All rights reserved. 
+     THIS SOFTWARE AND DATABASE IS PROVIDED "AS IS" AND PRINCETON   UNIVERSITY 
+MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR   IMPLIED.  BY WAY OF 
+EXAMPLE, BUT NOT LIMITATION, PRINCETON   UNIVERSITY MAKES NO REPRESENTATIONS 
+OR WARRANTIES OF MERCHANT-   ABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE 
+OR THAT THE USE   OF THE LICENSED SOFTWARE, DATABASE OR DOCUMENTATION 
+WILL NOT   INFRINGE ANY THIRD PARTY PATENTS, COPYRIGHTS, TRADEMARKS OR 
+  OTHER RIGHTS.      The name of Princeton University or Princeton may 
+not be used in   advertising or publicity pertaining to distribution of 
+the software   and/or database.  Title to copyright in this software, database 
+and   any associated documentation shall at all times remain with   Princeton 
+University and LICENSEE agrees to preserve same.   <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">DESCRIPTION</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wnpkgs.7WN.html

@@ -0,0 +1,95 @@
+ <!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WNPKGS(7WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+wnpkgs - description of various WordNet system packages  
+<H2><A NAME="sect1" HREF="#toc1">DESCRIPTION 
+</A></H2>
+WordNet 3.0 is distributed in several formats and in various packages. All 
+of the packages are available via anonymous FTP from <B>ftp.cogsci.princeton.edu 
+</B> and from the WordNet Web site at <B><A HREF="http://wordnet.princeton.edu">http://wordnet.princeton.edu</A>
+ </B>.  
+<H3><A NAME="sect2" HREF="#toc2">Packages 
+Available Via FTP and WWW </A></H3>
+The following WordNet packages can be downloaded 
+using a web browser from <B>ftp://ftp.cogsci.princeton.edu/wordnet/3.0 </B>, or from 
+the Web site noted above.  Users can also FTP directly from <B>ftp.cogsci.princeton.edu 
+</B>, directory <B>wordnet/3.0 </B>. <P>
+  <TABLE BORDER=0>
+ <TR> <TD ALIGN=CENTER><B>Package </B> </TD> <TD ALIGN=CENTER><B>Filename </B> </TD> <TD ALIGN=CENTER><B>Platform </B> </TD> <TD ALIGN=CENTER><B>Description 
+</B> </TD> </TR>
+ <TR>   <TR> <TD ALIGN=LEFT>Database </TD> <TD ALIGN=LEFT><B>WordNet-3.0.tar.gz </B> </TD> <TD ALIGN=LEFT>Unix/OS X </TD> <TD ALIGN=LEFT>WordNet 3.0 database, interfaces, 
+sense index, interface and library source code, documentation.  </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Database 
+</TD> <TD ALIGN=LEFT><B>WordNet-3.0.exe </B> </TD> <TD ALIGN=LEFT>Windows </TD> <TD ALIGN=LEFT>WordNet 3.0 database, interfaces, sense index, 
+interface and library source code, documentation.  </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Prolog Database </TD> 
+<TD ALIGN=LEFT><B>WNprolog-3.0.tar.gz </B> </TD> <TD ALIGN=LEFT>All </TD> <TD ALIGN=LEFT>WordNet 3.0 database files in Prolog-readable format, 
+documentation.  </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Sense Map </TD> <TD ALIGN=LEFT><B>WNsnsmap-3.0.tar.gz </B> </TD> <TD ALIGN=LEFT>All </TD> <TD ALIGN=LEFT>Mapping of 2.1 to 3.0 
+senses, documentation.  </TD> </TR>
+ </TABLE>
+ <P>
+  
+<H3><A NAME="sect3" HREF="#toc3">Database Package </A></H3>
+The database package is a 
+complete installation for WordNet 3.0 users. It includes the 3.0 database 
+files, source code for the WordNet browsers and library, and documentation. 
+ The other packages are not included - they must be downloaded and installed 
+separately. <P>
+ Note that with this version of WordNet for Unix platforms, 
+only source code is provided.  Users should carefully read the README and 
+INSTALL files for detailed information on compiling WordNet and dependencies. 
+<P>
+  
+<H3><A NAME="sect4" HREF="#toc4">Prolog Database Package </A></H3>
+The WordNet 3.0 database files are available 
+in this package in a Prolog-readable format.  Documentation describing the 
+file format is included.  This package is only downloadable in compressed 
+tar file format, although once unpackaged it can be used from Windows 
+systems since the files are in ASCII.  Many Windows utilities, such as 
+WinZip, can deal with a compressed tar file.  
+<H3><A NAME="sect5" HREF="#toc5">Sense Map Package </A></H3>
+To help 
+users automatically convert 2.1 noun and verb senses to their corresponding 
+3.0 senses, we provide sense mapping information in this package.  This 
+package contains files to map polysemous and monosemous words, and documentation 
+that describes the format of these files.  As with the Prolog database, 
+this package is only downloadable in compressed tar format, but the files 
+are also in ASCII.  
+<H2><A NAME="sect6" HREF="#toc6">NOTES </A></H2>
+The lexicographer files and <B><A HREF="grind.1WN.html">grind</B>(1WN)</A>
+ program 
+are not generally distributed. <P>
+ All of the packages described above may 
+not be available at the time of release of the 3.0 database package.  
+<H2><A NAME="sect7" HREF="#toc7">SEE 
+ALSO </A></H2>
+<B><A HREF="wnintro.1WN.html">wnintro</B>(1WN)</A>
+, <B><A HREF="wnintro.3WN.html">wnintro</B>(3WN)</A>
+, <B><A HREF="wnintro.5WN.html">wnintro</B>(5WN)</A>
+, <B><A HREF="wnintro.7WN.html">wnintro</B>(7WN)</A>
+. <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">DESCRIPTION</A></LI>
+<UL>
+<LI><A NAME="toc2" HREF="#sect2">Packages Available Via FTP and WWW</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">Database Package</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">Prolog Database Package</A></LI>
+<LI><A NAME="toc5" HREF="#sect5">Sense Map Package</A></LI>
+</UL>
+<LI><A NAME="toc6" HREF="#sect6">NOTES</A></LI>
+<LI><A NAME="toc7" HREF="#sect7">SEE ALSO</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wnsearch.3WN.html

@@ -0,0 +1,338 @@
+<!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WNSEARCH(3WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+findtheinfo, findtheinfo_ds, is_defined, in_wn, index_lookup, parse_index, 
+getindex, read_synset, parse_synset, free_syns, free_synset, free_index, 
+traceptrs_ds, do_trace  
+<H2><A NAME="sect1" HREF="#toc1">SYNOPSIS </A></H2>
+<P>
+<B>#include "wn.h" <P>
+<B>char *findtheinfo(char 
+*searchstr, int pos, int ptr_type, int sense_num); </B></B> <P>
+<B>SynsetPtr findtheinfo_ds(char 
+*searchstr, int pos, int ptr_type, int sense_num ); </B> <P>
+<B>unsigned int is_defined(char 
+*searchstr, int pos); </B> <P>
+<B>unsigned int in_wn(char *searchstr, int pos); </B> 
+<P>
+<B>IndexPtr index_lookup(char *searchstr, int pos); </B> <P>
+<B>IndexPtr parse_index(long 
+offset, int dabase, char *line); </B> <P>
+<B>IndexPtr getindex(char *searchstr, int 
+pos); </B> <P>
+<B>SynsetPtr read_synset(int pos, long synset_offset, char *searchstr); 
+</B> <P>
+<B>SynsetPtr parse_synset(FILE *fp, int pos, char *searchstr); </B> <P>
+<B>void free_syns(SynsetPtr 
+synptr); </B> <P>
+<B>void free_synset(SynsetPtr synptr); </B> <P>
+<B>void free_index(IndexPtr 
+idx); </B> <P>
+<B>SynsetPtr traceptrs_ds(SynsetPtr synptr, int ptr_type, int pos, 
+int depth); </B> <P>
+<B>char *do_trace(SynsetPtr synptr, int ptr_type, int pos, int 
+depth); </B>  
+<H2><A NAME="sect2" HREF="#toc2">DESCRIPTION </A></H2>
+<P>
+These functions are used for searching the WordNet 
+database.  They generally fall into several categories: functions for reading 
+and parsing index file entries; functions for reading and parsing synsets 
+in data files; functions for tracing pointers and hierarchies; functions 
+for freeing space occupied by data structures allocated with <B><A HREF="malloc.3.html">malloc</B>(3)</A>
+. 
+<P>
+ In the following function descriptions, <I>pos </I> is one of the following: 
+<P>
+  <blockquote><B>1 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;NOUN <BR>
+ <B>2 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;VERB <BR>
+ <B>3 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADJECTIVE <BR>
+ <B>4 </B><tt> </tt>&nbsp;<tt> </tt>&nbsp;ADVERB <BR>
+  </blockquote>
+<P>
+ <B>findtheinfo()</B> is the primary 
+search algorithm for use with database interface applications.  Search 
+results are automatically formatted, and a pointer to the text buffer 
+is returned.  All searches listed in  <B>WNHOME/include/wn.h</B> can be done by 
+ <B>findtheinfo()</B>. <B>findtheinfo_ds()</B> can be used to perform most of the searches, 
+with results returned in a linked list data structure.  This is for use 
+with applications that need to analyze the search results rather than 
+just display them. <P>
+ Both functions are passed the same arguments: <I>searchstr 
+</I> is the word or collocation to search for; <I>pos </I> indicates the syntactic 
+category to search in; <I>ptr_type </I> is one of the valid search types for 
+<I>searchstr </I> in <I>pos </I>.  (Available searches can be obtained by calling <B>is_defined()</B> 
+described below.)  <I>sense_num </I> should be <FONT SIZE=-1><B>ALLSENSES </B></FONT>
+  if the search is to 
+be done on all senses of <I>searchstr </I> in <I>pos </I>, or a positive integer indicating 
+which sense to search. <P>
+ <B>findtheinfo_ds() </B> returns a linked list data structures 
+representing synsets.  Senses are linked through the <I>nextss </I> field of a 
+<B>Synset </B> data structure.  For each sense, synsets that match the search 
+specified with <I>ptr_type </I> are linked through the <I>ptrlist </I> field.  See <FONT SIZE=-1><B>Synset 
+Navigation </B></FONT>
+  below, for detailed information on the linked lists returned. 
+<P>
+ <B>is_defined() </B> sets a bit for each search type that is valid for <I>searchstr 
+</I> in <I>pos </I>, and returns the resulting unsigned integer.  Each bit number 
+corresponds to a pointer type constant defined in <B>WNHOME/include/wn.h </B>. 
+ For example, if bit 2 is set, the <FONT SIZE=-1><B>HYPERPTR </B></FONT>
+  search is valid for <I>searchstr 
+</I>.  There are 29 possible searches. <P>
+ <B>in_wn() </B> is used to find the syntactic 
+categories in the WordNet database that contain one or more senses of 
+<I>searchstr </I>. If <I>pos </I> is <FONT SIZE=-1><B>ALL_POS, </B></FONT>
+  all syntactic categories are checked. 
+ Otherwise, only the part of speech passed is checked.  An unsigned integer 
+is returned with a bit set corresponding to each syntactic category containing 
+<I>searchstr </I>.  The bit number matches the number for the part of speech.  
+<B>0 </B> is returned if <I>searchstr </I> is not present in <I>pos </I>. <P>
+ <B>index_lookup() </B> finds 
+<I>searchstr </I> in the index file for <I>pos </I> and returns a pointer to the parsed 
+entry in an <B>Index </B> data structure.  <I>searchstr </I> must exactly match the form 
+of the word (lower case only, hyphens and underscores in the same places) 
+in the index file. <FONT SIZE=-1><B>NULL </B></FONT>
+  is returned if a match is not found. <P>
+ <B>parse_index() 
+</B> parses an entry from an index file and returns a pointer to the parsed 
+entry in an <B>Index </B> data structure. Passed the byte <I>offset </I> and syntactic 
+category, it reads the index entry at the desired location in the corresponding 
+file.  If passed <I>line </I>, <I>line </I> contains an index file entry and the database 
+index file is not consulted.  However, <I>offset </I> and <I>dbase </I> should still 
+be passed so the information can be stored in the <B>Index </B> structure. <P>
+ <B>getindex() 
+</B> is a "smart" search for <I>searchstr </I> in the index file corresponding to 
+<I>pos </I>.  It applies to <I>searchstr </I> an algorithm that replaces underscores 
+with hyphens, hyphens with underscores, removes hyphens and underscores, 
+and removes periods in an attempt to find a form of the string that is 
+an exact match for an entry in the index file corresponding to <I>pos </I>. <B>index_lookup() 
+</B> is called on each transformed string until a match is found or all the 
+different strings have been tried.  It returns a pointer to the parsed 
+<B>Index </B> data structure for <I>searchstr </I>, or <FONT SIZE=-1><B>NULL </B></FONT>
+  if a match is not found. 
+<P>
+ <B>read_synset() </B> is used to read a synset from a byte offset in a data 
+file.  It performs an <B><A HREF="fseek.3.html">fseek </B>(3)</A>
+ to <I>synset_offset </I> in the data file corresponding 
+to <I>pos </I>, and calls <B>parse_synset() </B> to read and parse the synset.  A pointer 
+to the <B>Synset </B> data structure containing the parsed synset is returned. 
+<P>
+ <B>parse_synset() </B> reads the synset at the current offset in the file indicated 
+by <I>fp </I>.  <I>pos </I> is the syntactic category, and <I>searchstr </I>, if not <FONT SIZE=-1><B>NULL, </B></FONT>
+ 
+ indicates the word in the synset that the caller is interested in.  An 
+attempt is made to match <I>searchstr </I> to one of the words in the synset. 
+ If an exact match is found, the <I>whichword </I> field in the <B>Synset </B> structure 
+is set to that word's number in the synset (beginning to count from <B>1 </B>). 
+<P>
+ <B>free_syns() </B> is used to free a linked list of <B>Synset </B> structures allocated 
+by <B>findtheinfo_ds() </B>.  <I>synptr </I> is a pointer to the list to free. <P>
+ <B>free_synset() 
+</B> frees the <B>Synset </B> structure pointed to by <I>synptr </I>. <P>
+ <B>free_index() </B> frees 
+the <B>Index </B> structure pointed to by <I>idx </I>. <P>
+ <B>traceptrs_ds() </B> is a recursive 
+search algorithm that traces pointers matching <I>ptr_type </I> starting with 
+the synset pointed to by <I>synptr </I>.  Setting <I>depth </I> to <B>1 </B> when <B>traceptrs_ds() 
+</B> is called indicates a recursive search; <B>0 </B> indicates a non-recursive call. 
+ <I>synptr </I> points to the data structure representing the synset to search 
+for a pointer of type <I>ptr_type </I>.  When a pointer type match is found, the 
+synset pointed to is read is linked onto the <I>nextss </I> chain.  Levels of 
+the tree generated by a recursive search are linked via the <I>ptrlist </I> field 
+structure until <FONT SIZE=-1><B>NULL </B></FONT>
+  is found, indicating the top (or bottom) of the 
+tree.  This function is usually called from <B>findtheinfo_ds() </B> for each 
+sense of the word.  See <FONT SIZE=-1><B>Synset Navigation </B></FONT>
+  below, for detailed information 
+on the linked lists returned. <P>
+ <B>do_trace() </B> performs the search indicated 
+by <I>ptr_type </I> on synset  synptr  in syntactic category <I>pos </I>.  <I>depth </I> is 
+defined as above.  <B>do_trace() </B> returns the search results formatted in 
+a text buffer.  
+<H3><A NAME="sect3" HREF="#toc3">Synset Navigation </A></H3>
+Since the <B>Synset </B> structure is used to 
+represent the synsets for both word senses and pointers, the <I>ptrlist </I> 
+and <I>nextss </I> fields have different meanings depending on whether the structure 
+is a word sense or pointer.  This can make navigation through the lists 
+returned by <B>findtheinfo_ds() </B> confusing. <P>
+ Navigation through the returned 
+list involves the following: <P>
+ Following the <I>nextss </I> chain from the synset 
+returned moves through the various senses of <I>searchstr </I>. <FONT SIZE=-1><B>NULL </B></FONT>
+  indicates 
+that end of the chain of senses. <P>
+ Following the <I>ptrlist </I> chain from a <B>Synset 
+</B> structure representing a sense traces the hierarchy of the search results 
+for that sense.  Subsequent links in the <I>ptrlist </I> chain indicate the next 
+level (up or down, depending on the search) in the hierarchy. <FONT SIZE=-1><B>NULL </B></FONT>
+  indicates 
+the end of the chain of search result synsets. <P>
+ If a synset pointed to 
+by <I>ptrlist </I> has a value in the <I>nextss </I> field, it represents another pointer 
+of the same type at that level in the hierarchy.  For example, some noun 
+synsets have two hypernyms.  Following this <I>nextss </I> pointer, and then the 
+<I>ptrlist </I> chain from the <B>Synset </B> structure pointed to, traces another, 
+parallel, hierarchy, until the end is indicated by <FONT SIZE=-1><B>NULL </B></FONT>
+  on that <I>ptrlist 
+</I> chain.  So, a <B>synset </B> representing a pointer (versus a sense of <I>searchstr 
+</I>) having a non-NULL value in <I>nextss </I> has another chain of search results 
+linked through the <I>ptrlist </I> chain of the synset pointed to by <I>nextss </I>. 
+<P>
+ If <I>searchstr </I> contains more than one base form in WordNet (as in the 
+noun <B>axes </B>, which has base forms <B>axe </B> and <B>axis </B>), synsets representing 
+the search results for each base form are linked through the <I>nextform 
+</I> pointer of the <B>Synset </B> structure.  
+<H3><A NAME="sect4" HREF="#toc4">WordNet Searches </A></H3>
+There is no extensive 
+description of what each search type is or the results returned.  Using 
+the WordNet interface, examining the source code, and reading <B><A HREF="wndb.5WN.html">wndb</B>(5WN)<B></B></A>
+ 
+are the best ways to see what types of searches are available and the 
+data returned for each. <P>
+ Listed below are the valid searches that can be 
+passed as <I>ptr_type </I> to <B>findtheinfo() </B>.  Passing a negative value (when 
+applicable) causes a recursive, hierarchical search by setting <I>depth </I> 
+to <B>1 </B> when <B>traceptrs() </B> is called. <P>
+   <TABLE BORDER=0>
+ <TR> <TD ALIGN=LEFT><B>ptr_type </B> </TD> <TD ALIGN=CENTER><B>Value </B> </TD> <TD ALIGN=CENTER><B>Pointer </B> </TD> <TD ALIGN=LEFT><B>Search 
+</B> </TD> </TR>
+ <TR> <TD ALIGN=LEFT> </TD> <TD ALIGN=CENTER> </TD> <TD ALIGN=CENTER><B>Symbol </B> </TD> </TR>
+ <TR>  <TR> <TD ALIGN=LEFT>ANTPTR </TD> <TD ALIGN=CENTER>1 </TD> <TD ALIGN=CENTER>! </TD> <TD ALIGN=LEFT>Antonyms </TD> </TR>
+ <TR> <TD ALIGN=LEFT>HYPERPTR </TD> <TD ALIGN=CENTER>2 </TD> <TD ALIGN=CENTER>@ </TD> <TD ALIGN=LEFT>Hypernyms 
+</TD> </TR>
+ <TR> <TD ALIGN=LEFT>HYPOPTR </TD> <TD ALIGN=CENTER>3 </TD> <TD ALIGN=CENTER>&nbsp; </TD> <TD ALIGN=LEFT>Hyponyms </TD> </TR>
+ <TR> <TD ALIGN=LEFT>ENTAILPTR </TD> <TD ALIGN=CENTER>4 </TD> <TD ALIGN=CENTER>* </TD> <TD ALIGN=LEFT>Entailment </TD> </TR>
+ <TR> <TD ALIGN=LEFT>SIMPTR </TD> <TD ALIGN=CENTER>5 
+</TD> <TD ALIGN=CENTER>&amp; </TD> <TD ALIGN=LEFT>Similar </TD> </TR>
+ <TR> <TD ALIGN=LEFT>ISMEMBERPTR </TD> <TD ALIGN=CENTER>6 </TD> <TD ALIGN=CENTER>#m </TD> <TD ALIGN=LEFT>Member meronym </TD> </TR>
+ <TR> <TD ALIGN=LEFT>ISSTUFFPTR </TD> <TD ALIGN=CENTER>7 </TD> <TD ALIGN=CENTER>#s 
+</TD> <TD ALIGN=LEFT>Substance meronym </TD> </TR>
+ <TR> <TD ALIGN=LEFT>ISPARTPTR </TD> <TD ALIGN=CENTER>8 </TD> <TD ALIGN=CENTER>#p </TD> <TD ALIGN=LEFT>Part meronym </TD> </TR>
+ <TR> <TD ALIGN=LEFT>HASMEMBERPTR </TD> 
+<TD ALIGN=CENTER>9 </TD> <TD ALIGN=CENTER>%m </TD> <TD ALIGN=LEFT>Member holonym </TD> </TR>
+ <TR> <TD ALIGN=LEFT>HASSTUFFPTR </TD> <TD ALIGN=CENTER>10 </TD> <TD ALIGN=CENTER>%s </TD> <TD ALIGN=LEFT>Substance holonym </TD> </TR>
+ <TR> <TD ALIGN=LEFT>HASPARTPTR 
+</TD> <TD ALIGN=CENTER>11 </TD> <TD ALIGN=CENTER>%p </TD> <TD ALIGN=LEFT>Part holonym </TD> </TR>
+ <TR> <TD ALIGN=LEFT>MERONYM </TD> <TD ALIGN=CENTER>12 </TD> <TD ALIGN=CENTER>% </TD> <TD ALIGN=LEFT>All meronyms </TD> </TR>
+ <TR> <TD ALIGN=LEFT>HOLONYM </TD> <TD ALIGN=CENTER>13 </TD> 
+<TD ALIGN=CENTER># </TD> <TD ALIGN=LEFT>All holonyms </TD> </TR>
+ <TR> <TD ALIGN=LEFT>CAUSETO </TD> <TD ALIGN=CENTER>14 </TD> <TD ALIGN=CENTER>&gt; </TD> <TD ALIGN=LEFT>Cause </TD> </TR>
+ <TR> <TD ALIGN=LEFT>PPLPTR </TD> <TD ALIGN=CENTER>15 </TD> <TD ALIGN=CENTER>&lt; </TD> <TD ALIGN=LEFT>Participle of 
+verb </TD> </TR>
+ <TR> <TD ALIGN=LEFT>SEEALSOPTR </TD> <TD ALIGN=CENTER>16 </TD> <TD ALIGN=CENTER>^ </TD> <TD ALIGN=LEFT>Also see </TD> </TR>
+ <TR> <TD ALIGN=LEFT>PERTPTR </TD> <TD ALIGN=CENTER>17 </TD> <TD ALIGN=CENTER>\ </TD> <TD ALIGN=LEFT>Pertains to noun 
+or derived from adjective </TD> </TR>
+ <TR> <TD ALIGN=LEFT>ATTRIBUTE </TD> <TD ALIGN=CENTER>18 </TD> <TD ALIGN=CENTER>\= </TD> <TD ALIGN=LEFT>Attribute </TD> </TR>
+ <TR> <TD ALIGN=LEFT>VERBGROUP 
+</TD> <TD ALIGN=CENTER>19 </TD> <TD ALIGN=CENTER>$ </TD> <TD ALIGN=LEFT>Verb group </TD> </TR>
+ <TR> <TD ALIGN=LEFT>DERIVATION </TD> <TD ALIGN=CENTER>20 </TD> <TD ALIGN=CENTER>+ </TD> <TD ALIGN=LEFT>Derivationally related form </TD> 
+</TR>
+ <TR> <TD ALIGN=LEFT>CLASSIFICATION </TD> <TD ALIGN=CENTER>21 </TD> <TD ALIGN=CENTER>; </TD> <TD ALIGN=LEFT>Domain of synset </TD> </TR>
+ <TR> <TD ALIGN=LEFT>CLASS </TD> <TD ALIGN=CENTER>22 </TD> <TD ALIGN=CENTER>- </TD> <TD ALIGN=LEFT>Member of this 
+domain </TD> </TR>
+ <TR> <TD ALIGN=LEFT>SYNS </TD> <TD ALIGN=CENTER>23 </TD> <TD ALIGN=CENTER><I>n/a </I> </TD> <TD ALIGN=LEFT>Find synonyms  </TD> </TR>
+ <TR> <TD ALIGN=LEFT>FREQ </TD> <TD ALIGN=CENTER>24 </TD> <TD ALIGN=CENTER><I>n/a </I> </TD> <TD ALIGN=LEFT>Polysemy </TD> 
+</TR>
+ <TR> <TD ALIGN=LEFT>FRAMES </TD> <TD ALIGN=CENTER>25 </TD> <TD ALIGN=CENTER><I>n/a </I> </TD> <TD ALIGN=LEFT>Verb example sentences and generic frames </TD> </TR>
+ <TR> <TD ALIGN=LEFT>COORDS 
+</TD> <TD ALIGN=CENTER>26 </TD> <TD ALIGN=CENTER><I>n/a </I> </TD> <TD ALIGN=LEFT>Noun coordinates </TD> </TR>
+ <TR> <TD ALIGN=LEFT>RELATIVES </TD> <TD ALIGN=CENTER>27 </TD> <TD ALIGN=CENTER><I>n/a </I> </TD> <TD ALIGN=LEFT>Group related senses 
+</TD> </TR>
+ <TR> <TD ALIGN=LEFT>HMERONYM </TD> <TD ALIGN=CENTER>28 </TD> <TD ALIGN=CENTER><I>n/a </I> </TD> <TD ALIGN=LEFT>Hierarchical meronym search </TD> </TR>
+ <TR> <TD ALIGN=LEFT>HHOLONYM </TD> <TD ALIGN=CENTER>29 </TD> <TD ALIGN=CENTER><I>n/a 
+</I> </TD> <TD ALIGN=LEFT>Hierarchical holonym search </TD> </TR>
+ <TR> <TD ALIGN=LEFT>WNGREP </TD> <TD ALIGN=CENTER>30 </TD> <TD ALIGN=CENTER><I>n/a </I> </TD> <TD ALIGN=LEFT>Find keywords by substring 
+</TD> </TR>
+ <TR> <TD ALIGN=LEFT>OVERVIEW </TD> <TD ALIGN=CENTER>31 </TD> <TD ALIGN=CENTER><I>n/a </I> </TD> <TD ALIGN=LEFT>Show all synsets for word </TD> </TR>
+ <TR> <TD ALIGN=LEFT>CLASSIF_CATEGORY </TD> 
+<TD ALIGN=CENTER>32 </TD> <TD ALIGN=CENTER>;c </TD> <TD ALIGN=LEFT>Show domain topic </TD> </TR>
+ <TR> <TD ALIGN=LEFT>CLASSIF_USAGE </TD> <TD ALIGN=CENTER>33 </TD> <TD ALIGN=CENTER>;u </TD> <TD ALIGN=LEFT>Show domain usage 
+</TD> </TR>
+ <TR> <TD ALIGN=LEFT>CLASSIF_REGIONAL </TD> <TD ALIGN=CENTER>34 </TD> <TD ALIGN=CENTER>;r </TD> <TD ALIGN=LEFT>Show domain region </TD> </TR>
+ <TR> <TD ALIGN=LEFT>CLASS_CATEGORY </TD> <TD ALIGN=CENTER>35 
+</TD> <TD ALIGN=CENTER>-c </TD> <TD ALIGN=LEFT>Show domain terms for topic </TD> </TR>
+ <TR> <TD ALIGN=LEFT>CLASS_USAGE </TD> <TD ALIGN=CENTER>36 </TD> <TD ALIGN=CENTER>-u </TD> <TD ALIGN=LEFT>Show domain terms 
+for usage </TD> </TR>
+ <TR> <TD ALIGN=LEFT>CLASS_REGIONAL </TD> <TD ALIGN=CENTER>37 </TD> <TD ALIGN=CENTER>-r </TD> <TD ALIGN=LEFT>Show domain terms for region </TD> </TR>
+ <TR> <TD ALIGN=LEFT>INSTANCE 
+</TD> <TD ALIGN=CENTER>38 </TD> <TD ALIGN=CENTER>@i </TD> <TD ALIGN=LEFT>Instance of </TD> </TR>
+ <TR> <TD ALIGN=LEFT>INSTANCES </TD> <TD ALIGN=CENTER>39 </TD> <TD ALIGN=CENTER>&nbsp;i </TD> <TD ALIGN=LEFT>Show instances </TD> </TR>
+ </TABLE>
+<P>
+ <B>findtheinfo_ds() 
+</B> cannot perform the following searches: <P>
+  <blockquote>SEEALSOPTR <BR>
+ PERTPTR <BR>
+ VERBGROUP 
+<BR>
+ FREQ <BR>
+ FRAMES <BR>
+ RELATIVES <BR>
+ WNGREP <BR>
+ OVERVIEW <BR>
+  </blockquote>
+ 
+<H2><A NAME="sect5" HREF="#toc5">NOTES </A></H2>
+Applications that 
+use WordNet and/or the morphological functions must call <B>wninit() </B> at 
+the start of the program.  See <B><A HREF="wnutil.3WN.html">wnutil</B>(3WN)</A>
+ for more information. <P>
+ In all 
+function calls, <I>searchstr </I> may be either a word or a collocation formed 
+by joining individual words with underscore characters (<B>_ </B>). <P>
+ The <B>SearchResults 
+</B> structure defines fields in the <I>wnresults </I> global variable that are set 
+by the various search functions.  This is a way to get additional information, 
+such as the number of senses the word has, from the search functions. The 
+<I>searchds </I> field is set by <B>findtheinfo_ds() </B>. <P>
+ The <I>pos </I> passed to <B>traceptrs_ds() 
+</B> is not used. <P>
+  
+<H2><A NAME="sect6" HREF="#toc6">SEE ALSO </A></H2>
+<B><A HREF="wn.1WN.html">wn</B>(1WN)</A>
+, <B><A HREF="wnb.1WN.html">wnb</B>(1WN)</A>
+, <B><A HREF="wnintro.3WN.html">wnintro</B>(3WN)</A>
+, <B><A HREF="binsrch.3WN.html">binsrch</B>(3WN)</A>
+, 
+<B><A HREF="malloc.3.html">malloc</B>(3)</A>
+, <B><A HREF="morph.3WN.html">morph</B>(3WN)</A>
+, <B><A HREF="wnutil.3WN.html">wnutil</B>(3WN)</A>
+, <B><A HREF="wnintro.5WN.html">wnintro</B>(5WN)</A>
+.  
+<H2><A NAME="sect7" HREF="#toc7">WARNINGS </A></H2>
+<B>parse_synset() 
+</B> must find an exact match between the <I>searchstr </I> passed and a word in 
+the synset to set <I>whichword </I>.  No attempt is made to translate hyphens 
+and underscores, as is done in <B>getindex() </B>. <P>
+ The WordNet database and exception 
+list files must be opened with <B>wninit </B> prior to using any of the searching 
+functions. <P>
+ A large search may cause <B>findtheinfo() </B> to run out of buffer 
+space.  The maximum buffer size is determined by computer platform. If the 
+buffer size is exceeded the following message is printed in the output 
+buffer: <B>"Search too large.  Narrow search and try again..." </B>. <P>
+ Passing an invalid 
+<I>pos </I> will probably result in a core dump. <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">SYNOPSIS</A></LI>
+<LI><A NAME="toc2" HREF="#sect2">DESCRIPTION</A></LI>
+<UL>
+<LI><A NAME="toc3" HREF="#sect3">Synset Navigation</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">WordNet Searches</A></LI>
+</UL>
+<LI><A NAME="toc5" HREF="#sect5">NOTES</A></LI>
+<LI><A NAME="toc6" HREF="#sect6">SEE ALSO</A></LI>
+<LI><A NAME="toc7" HREF="#sect7">WARNINGS</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wnstats.7WN.html

@@ -0,0 +1,80 @@
+<!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WNSTATS(7WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+wnstats - WordNet 3.0 database statistics  
+<H2><A NAME="sect1" HREF="#toc1">DESCRIPTION </A></H2>
+ 
+<H3><A NAME="sect2" HREF="#toc2">Number of 
+words, synsets, and senses </A></H3>
+ <TABLE BORDER=0>
+ <TR> <TD ALIGN=CENTER><B>POS </B> </TD> <TD ALIGN=CENTER><B>Unique </B> </TD> <TD ALIGN=CENTER><B>Synsets </B> </TD> <TD ALIGN=CENTER><B>Total </B> </TD> </TR>
+ <TR> <TD ALIGN=CENTER> </TD> <TD ALIGN=CENTER><B>Strings 
+</B> </TD> <TD ALIGN=CENTER> </TD> <TD ALIGN=CENTER><B>Word-Sense Pairs </B> </TD> </TR>
+ <TR>  <TR> <TD ALIGN=LEFT>Noun </TD> <TD ALIGN=RIGHT>117798 </TD> <TD ALIGN=RIGHT>82115 </TD> <TD ALIGN=RIGHT>146312 </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Verb </TD> <TD ALIGN=RIGHT>11529 </TD> 
+<TD ALIGN=RIGHT>13767 </TD> <TD ALIGN=RIGHT>25047 </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Adjective </TD> <TD ALIGN=RIGHT>21479 </TD> <TD ALIGN=RIGHT>18156 </TD> <TD ALIGN=RIGHT>30002 </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Adverb </TD> <TD ALIGN=RIGHT>4481 </TD> <TD ALIGN=RIGHT>3621 </TD> 
+<TD ALIGN=RIGHT>5580 </TD> </TR>
+ <TR>  <TR> <TD ALIGN=LEFT>Totals </TD> <TD ALIGN=RIGHT>155287 </TD> <TD ALIGN=RIGHT>117659 </TD> <TD ALIGN=RIGHT>206941 </TD> </TR>
+ </TABLE>
+<P>
+  
+<H3><A NAME="sect3" HREF="#toc3">Polysemy information </A></H3>
+<P>
+  <TABLE BORDER=0>
+ <TR> 
+<TD ALIGN=CENTER><B>POS </B> </TD> <TD ALIGN=CENTER><B>Monosemous </B> </TD> <TD ALIGN=CENTER><B>Polysemous </B> </TD> <TD ALIGN=CENTER><B>Polysemous </B> </TD> </TR>
+ <TR> <TD ALIGN=CENTER> </TD> <TD ALIGN=CENTER><B>Words and Senses </B> </TD> <TD ALIGN=CENTER><B>Words 
+</B> </TD> <TD ALIGN=CENTER><B>Senses </B> </TD> </TR>
+ <TR>  <TR> <TD ALIGN=LEFT>Noun </TD> <TD ALIGN=RIGHT>101863 </TD> <TD ALIGN=RIGHT>15935 </TD> <TD ALIGN=RIGHT>44449 </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Verb </TD> <TD ALIGN=RIGHT>6277 </TD> <TD ALIGN=RIGHT>5252 </TD> <TD ALIGN=RIGHT>18770 </TD> 
+</TR>
+ <TR> <TD ALIGN=LEFT>Adjective </TD> <TD ALIGN=RIGHT>16503 </TD> <TD ALIGN=RIGHT>4976 </TD> <TD ALIGN=RIGHT>14399 </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Adverb </TD> <TD ALIGN=RIGHT>3748 </TD> <TD ALIGN=RIGHT>733 </TD> <TD ALIGN=RIGHT>1832 </TD> </TR>
+ <TR>  <TR> <TD ALIGN=LEFT>Totals 
+</TD> <TD ALIGN=RIGHT>128391 </TD> <TD ALIGN=RIGHT>26896 </TD> <TD ALIGN=RIGHT>79450 </TD> </TR>
+ </TABLE>
+<P>
+  <TABLE BORDER=0>
+ <TR> <TD ALIGN=CENTER><B>POS </B> </TD> <TD ALIGN=CENTER><B>Average Polysemy </B> </TD> <TD ALIGN=CENTER><B>Average Polysemy 
+</B> </TD> </TR>
+ <TR> <TD ALIGN=CENTER> </TD> <TD ALIGN=CENTER><B>Including Monosemous Words </B> </TD> <TD ALIGN=CENTER><B>Excluding Monosemous Words </B> </TD> </TR>
+ <TR>  <TR> <TD ALIGN=LEFT>Noun 
+</TD> <TD ALIGN=RIGHT>1.24 </TD> <TD ALIGN=RIGHT>2.79 </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Verb </TD> <TD ALIGN=RIGHT>2.17 </TD> <TD ALIGN=RIGHT>3.57 </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Adjective </TD> <TD ALIGN=RIGHT>1.40 </TD> <TD ALIGN=RIGHT>2.71 </TD> </TR>
+ <TR> <TD ALIGN=LEFT>Adverb </TD> <TD ALIGN=RIGHT>1.25 </TD> <TD ALIGN=RIGHT>2.50 
+</TD> </TR>
+ </TABLE>
+<P>
+  
+<H2><A NAME="sect4" HREF="#toc4">NOTES </A></H2>
+Statistics for all types of adjectives and adjective satellites 
+are combined.   <P>
+ The total of all unique noun, verb, adjective, and adverb 
+strings is actually 147278. However, many strings are unique within a syntactic 
+category, but are in more than one syntactic category.  The figures in 
+the table represent the unique strings in each syntactic category. <P>
+ <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">DESCRIPTION</A></LI>
+<UL>
+<LI><A NAME="toc2" HREF="#sect2">Number of words, synsets, and senses</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">Polysemy information</A></LI>
+</UL>
+<LI><A NAME="toc4" HREF="#sect4">NOTES</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/html/wnutil.3WN.html

@@ -0,0 +1,154 @@
+<!-- manual page source format generated by PolyglotMan v3.0.3a12, -->
+<!-- available via anonymous ftp from ftp.cs.berkeley.edu:/ucb/people/phelps/tcltk/rman.tar.Z -->
+
+<HTML>
+<HEAD>
+<TITLE>WNUTIL(3WN) manual page</TITLE>
+</HEAD>
+<BODY>
+<A HREF="#toc">Table of Contents</A><P>
+ 
+<H2><A NAME="sect0" HREF="#toc0">NAME </A></H2>
+wninit, re_wninit, cntwords, strtolower, ToLowerCase, strsubst, 
+getptrtype, getpos, getsstype, StrToPos, GetSynsetForSense, GetDataOffset, 
+GetPolyCount, WNSnsToStr, GetValidIndexPointer, GetWNSense, GetSenseIndex, 
+default_display_message  
+<H2><A NAME="sect1" HREF="#toc1">SYNOPSIS </A></H2>
+<P>
+<B>#include "wn.h" </B> <P>
+<B>int wninit(void); </B> <P>
+<B>int 
+re_wninit(void); </B> <P>
+<B>int cntwords(char *str, char separator); </B> <P>
+<B>char *strtolower(char 
+*str); </B> <P>
+<B>char *ToLowerCase(char *str); </B> <P>
+<B>char *strsubst(char *str, char 
+from, char to); </B> <P>
+<B>int getptrtype(char *ptr_symbol); </B> <P>
+<B>int getpos(char *ss_type); 
+</B> <P>
+<B>int getsstype(char *ss_type); </B> <P>
+<B>int StrToPos(char pos); </B> <P>
+<B>SynsetPtr GetSynsetForSense(char 
+*sense_key); </B> <P>
+<B>long GetDataOffset(char *sense_key); </B> <P>
+<B>int GetPolyCount(char 
+*sense_key); </B> <P>
+<B>char *WNSnsToStr(IndexPtr idx, int sense_num); </B> <P>
+<B>IndexPtr 
+GetValidIndexPointer(char *str, int pos); </B> <P>
+<B>int GetWNSense(char *lemma, 
+*lex_sense); </B> <P>
+<B>SnsIndexPtr GetSenseIndex(char *sense_key); </B> <P>
+<B>int GetTagcnt(IndexPtr 
+idx, int sense); </B> <P>
+<B>int default_display_message(char *msg); </B>  
+<H2><A NAME="sect2" HREF="#toc2">DESCRIPTION 
+</A></H2>
+<P>
+The WordNet library contains many utility functions used by the interface 
+code, other library functions, and various applications and tools.  Only 
+those of importance to the WordNet search code, or which are generally 
+useful are described here. <P>
+ <B>wninit()</B> opens the files necessary for using 
+WordNet with the WordNet library functions.  The database files are opened, 
+and  <B>morphinit()</B> is called to open the exception list files.  Returns <B>0 
+</B> if successful, <B>-1 </B> otherwise.  The database and exception list files must 
+be open before the WordNet search and morphology functions are used.  If 
+the database is successfully opened, the global variable <B>OpenDB </B> is set 
+to <B>1 </B>.  Note that it is possible for the database files to be opened (<B>OpenDB 
+== 1 </B>), but not the exception list files. <P>
+ <B>re_wninit()</B> is used to close 
+the database files and reopen them, and is used exclusively for WordNet 
+development. <B>re_morphinit() </B> is called to close and reopen the exception 
+list files.  Return codes are as described above. <P>
+ <B>cntwords()</B> counts the 
+number of underscore or space separated words in <I>str </I>. A hyphen is passed 
+in <I>separator </I> if is is to be considered a word delimiter.  Otherwise <I>separator 
+</I> can be any other character, or an underscore if another character is 
+not desired. <P>
+ <B>strtolower()</B> converts <I>str </I> to lower case and removes a trailing 
+adjective marker, if present.  <I>str </I> is actually modified by this function, 
+and a pointer to the modified string is returned. <P>
+ <B>ToLowerCase()</B> converts 
+<I>str </I> to lower case as above, without removing an adjective marker. <P>
+ <B>strsubst()</B> 
+replaces all occurrences of <I>from </I> with <I>to </I> in <I>str </I> and returns resulting 
+string. <P>
+ <B>getptrtype()</B> returns the integer <I>ptr_type </I> corresponding to the 
+pointer character passed in <I>ptr_symbol </I>.  See <B><A HREF="wnsearch.3WN.html">wnsearch</B>(3WN)</A>
+ for a table 
+of pointer symbols and types. <P>
+ <B>getpos()</B> returns the integer constant corresponding 
+to the synset type passed. <I>ss_type </I> may be one of the following: <B>n, v, 
+a, r, s </B>.  If <B>s </B> is passed, <FONT SIZE=-1><B>ADJ </B></FONT>
+  is returned.  Exits with <B>-1 </B> if <I>ss_type 
+</I> is invalid. <P>
+ <B>getsstype()</B> works like <B>getpos() </B>, but returns <FONT SIZE=-1><B>SATELLITE </B></FONT>
+ 
+ if <I>ss_type </I> is <B>s </B>. <P>
+ <B>StrToPos()</B> returns the integer constant corresponding 
+to the syntactic category passed in <I>pos </I>.  <I>string </I> must be one of the following: 
+<B>noun, verb, adj, adv </B>.  <B>-1 </B> is returned if <I>pos </I> is invalid. <P>
+ <B>GetSynsetForSense()</B> 
+returns the synset that contains the word sense <I>sense_key </I> and <FONT SIZE=-1><B>NULL </B></FONT>
+  
+in case of error. <P>
+ <B>GetDataOffset()</B> returns the synset offset for synset 
+that contains the word sense <I>sense_key </I>, and <B>0 </B> if <I>sense_key </I> is not in 
+sense index file.  <P>
+ <B>GetPolyCount()</B> returns the polysemy count (number of 
+senses in WordNet) for <I>lemma </I> encoded in <I>sense_key </I> and <B>0 </B> if word is 
+not found.  <P>
+ <B>WNSnsToStr()</B> returns sense key encoding for <I>sense_num </I> entry 
+in <I>idx </I>. <P>
+ <B>GetValidIndexPointer()</B> returns the Index structure for <I>word </I> 
+in <I>pos </I>.  Calls <B><A HREF="morphstr.3WN.html">morphstr</B>(3WN)</A>
+ to find a valid base form if <I>word </I> is inflected. 
+<P>
+ <B>GetWNSense()</B> returns the WordNet sense number for the sense key encoding 
+represented by <I>lemma </I> and <I>lex_sense </I>. <P>
+ <B>GetSenseIndex()</B> returns parsed sense 
+index entry for <I>sense_key </I> and  <FONT SIZE=-1><B>NULL </B></FONT>
+  if <I>sense_key </I> is not in sense index. 
+<P>
+ <B>GetTagcnt()</B> returns the number of times the sense passed has been tagged 
+according to the <I>cntlist </I> file. <P>
+ <B>default_display_message()</B> simply returns 
+<B>-1 </B>.  This is the default value for the global variable <B>display_message 
+</B>, that points to a function to call to display an error message.  In general, 
+applications (including the WordNet interfaces) define an application 
+specific function and set <B>display_message </B> to point to it.  
+<H2><A NAME="sect3" HREF="#toc3">NOTES </A></H2>
+<B>include/wn.h 
+</B> lists all the pointer and search types and their corresponding constant 
+values.  There is no description of what each search type is or the results 
+returned. Using the WordNet interface is the best way to see what types 
+of searches are available, and the data returned for each.  
+<H2><A NAME="sect4" HREF="#toc4">SEE ALSO </A></H2>
+<B><A HREF="wnintro.3WN.html">wnintro</B>(3WN)</A>
+, 
+<B><A HREF="wnsearch.3WN.html">wnsearch</B>(3WN)</A>
+, <B><A HREF="morph.3WN.html">morph</B>(3WN)</A>
+, <B><A HREF="wnintro.5WN.html">wnintro</B>(5WN)</A>
+, <B><A HREF="wnintro.7WN.html">wnintro</B>(7WN)</A>
+. <P>
+  
+<H2><A NAME="sect5" HREF="#toc5">WARNINGS </A></H2>
+Error 
+checking on passed arguments is not rigorous.  Passing  <FONT SIZE=-1><B>NULL </B></FONT>
+  pointers 
+or invalid values will often cause an application to die. <P>
+
+<HR><P>
+<A NAME="toc"><B>Table of Contents</B></A><P>
+<UL>
+<LI><A NAME="toc0" HREF="#sect0">NAME</A></LI>
+<LI><A NAME="toc1" HREF="#sect1">SYNOPSIS</A></LI>
+<LI><A NAME="toc2" HREF="#sect2">DESCRIPTION</A></LI>
+<LI><A NAME="toc3" HREF="#sect3">NOTES</A></LI>
+<LI><A NAME="toc4" HREF="#sect4">SEE ALSO</A></LI>
+<LI><A NAME="toc5" HREF="#sect5">WARNINGS</A></LI>
+</UL>
+</BODY></HTML>

corpora/en/wordnet/doc/man/Makefile

@@ -0,0 +1,478 @@
+# Makefile.in generated by automake 1.9 from Makefile.am.
+# doc/man/Makefile.  Generated from Makefile.in by configure.
+
+# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
+# 2003, 2004  Free Software Foundation, Inc.
+# This Makefile.in is free software; the Free Software Foundation
+# gives unlimited permission to copy and/or distribute it,
+# with or without modifications, as long as this notice is preserved.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
+# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+# PARTICULAR PURPOSE.
+
+
+srcdir = .
+top_srcdir = ../..
+
+pkgdatadir = $(datadir)/WordNet
+pkglibdir = $(libdir)/WordNet
+pkgincludedir = $(includedir)/WordNet
+top_builddir = ../..
+am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd
+INSTALL = /usr/csl/bin/install -c
+install_sh_DATA = $(install_sh) -c -m 644
+install_sh_PROGRAM = $(install_sh) -c
+install_sh_SCRIPT = $(install_sh) -c
+INSTALL_HEADER = $(INSTALL_DATA)
+transform = $(program_transform_name)
+NORMAL_INSTALL = :
+PRE_INSTALL = :
+POST_INSTALL = :
+NORMAL_UNINSTALL = :
+PRE_UNINSTALL = :
+POST_UNINSTALL = :
+subdir = doc/man
+DIST_COMMON = $(srcdir)/Makefile.am $(srcdir)/Makefile.in
+ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
+am__aclocal_m4_deps = $(top_srcdir)/acinclude.m4 \
+	$(top_srcdir)/configure.ac
+am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
+	$(ACLOCAL_M4)
+mkinstalldirs = $(install_sh) -d
+CONFIG_HEADER = $(top_builddir)/config.h
+CONFIG_CLEAN_FILES =
+SOURCES =
+DIST_SOURCES =
+man1dir = $(mandir)/man1
+am__installdirs = "$(DESTDIR)$(man1dir)" "$(DESTDIR)$(man3dir)" \
+	"$(DESTDIR)$(man5dir)" "$(DESTDIR)$(man7dir)"
+man3dir = $(mandir)/man3
+man5dir = $(mandir)/man5
+man7dir = $(mandir)/man7
+NROFF = nroff
+MANS = $(man_MANS)
+DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
+ACLOCAL = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run aclocal-1.9
+AMDEP_FALSE = #
+AMDEP_TRUE = 
+AMTAR = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run tar
+AUTOCONF = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run autoconf
+AUTOHEADER = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run autoheader
+AUTOMAKE = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run automake-1.9
+AWK = nawk
+CC = gcc
+CCDEPMODE = depmode=gcc3
+CFLAGS = -g -O2
+CPP = gcc -E
+CPPFLAGS = 
+CYGPATH_W = echo
+DEFS = -DHAVE_CONFIG_H
+DEPDIR = .deps
+ECHO_C = 
+ECHO_N = -n
+ECHO_T = 
+EGREP = egrep
+EXEEXT = 
+INSTALL_DATA = ${INSTALL} -m 644
+INSTALL_PROGRAM = ${INSTALL}
+INSTALL_SCRIPT = ${INSTALL}
+INSTALL_STRIP_PROGRAM = ${SHELL} $(install_sh) -c -s
+LDFLAGS = 
+LIBOBJS = 
+LIBS = 
+LTLIBOBJS = 
+MAKEINFO = ${SHELL} /people/wn/src/Release/3.0/Unix/missing --run makeinfo
+OBJEXT = o
+PACKAGE = WordNet
+PACKAGE_BUGREPORT = wordnet@princeton.edu
+PACKAGE_NAME = WordNet
+PACKAGE_STRING = WordNet 3.0
+PACKAGE_TARNAME = wordnet
+PACKAGE_VERSION = 3.0
+PATH_SEPARATOR = :
+RANLIB = ranlib
+SET_MAKE = 
+SHELL = /bin/bash
+STRIP = 
+TCL_INCLUDE_SPEC = -I/usr/csl/include
+TCL_LIB_SPEC = -L/usr/csl/lib -ltcl8.4
+TK_LIBS = -L/usr/openwin/lib -lX11 -ldl  -lpthread -lsocket -lnsl -lm
+TK_LIB_SPEC = -L/usr/csl/lib -ltk8.4
+TK_PREFIX = /usr/csl
+TK_XINCLUDES = -I/usr/openwin/include
+VERSION = 3.0
+ac_ct_CC = gcc
+ac_ct_RANLIB = ranlib
+ac_ct_STRIP = 
+ac_prefix = /usr/local/WordNet-3.0
+am__fastdepCC_FALSE = #
+am__fastdepCC_TRUE = 
+am__include = include
+am__leading_dot = .
+am__quote = 
+am__tar = ${AMTAR} chof - "$$tardir"
+am__untar = ${AMTAR} xf -
+bindir = ${exec_prefix}/bin
+build_alias = 
+datadir = ${prefix}/share
+exec_prefix = ${prefix}
+host_alias = 
+includedir = ${prefix}/include
+infodir = ${prefix}/info
+install_sh = /people/wn/src/Release/3.0/Unix/install-sh
+libdir = ${exec_prefix}/lib
+libexecdir = ${exec_prefix}/libexec
+localstatedir = ${prefix}/var
+mandir = ${prefix}/man
+mkdir_p = $(install_sh) -d
+oldincludedir = /usr/include
+prefix = /usr/local/WordNet-3.0
+program_transform_name = s,x,x,
+sbindir = ${exec_prefix}/sbin
+sharedstatedir = ${prefix}/com
+sysconfdir = ${prefix}/etc
+target_alias = 
+man_MANS = binsrch.3 cntlist.5 grind.1 lexnames.5 morph.3 morphy.7 senseidx.5 uniqbeg.7 wn.1 wnb.1 wndb.5 wngloss.7 wngroups.7 wninput.5 wnintro.1 wnintro.3 wnintro.5 wnintro.7 wnlicens.7 wnpkgs.7 wnsearch.3 wnstats.7 wnutil.3
+all: all-am
+
+.SUFFIXES:
+$(srcdir)/Makefile.in:  $(srcdir)/Makefile.am  $(am__configure_deps)
+	@for dep in $?; do \
+	  case '$(am__configure_deps)' in \
+	    *$$dep*) \
+	      cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh \
+		&& exit 0; \
+	      exit 1;; \
+	  esac; \
+	done; \
+	echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu  doc/man/Makefile'; \
+	cd $(top_srcdir) && \
+	  $(AUTOMAKE) --gnu  doc/man/Makefile
+.PRECIOUS: Makefile
+Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status
+	@case '$?' in \
+	  *config.status*) \
+	    cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \
+	  *) \
+	    echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)'; \
+	    cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \
+	esac;
+
+$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+
+$(top_srcdir)/configure:  $(am__configure_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+$(ACLOCAL_M4):  $(am__aclocal_m4_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+uninstall-info-am:
+install-man1: $(man1_MANS) $(man_MANS)
+	@$(NORMAL_INSTALL)
+	test -z "$(man1dir)" || $(mkdir_p) "$(DESTDIR)$(man1dir)"
+	@list='$(man1_MANS) $(dist_man1_MANS) $(nodist_man1_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.1*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  if test -f $(srcdir)/$$i; then file=$(srcdir)/$$i; \
+	  else file=$$i; fi; \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    1*) ;; \
+	    *) ext='1' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " $(INSTALL_DATA) '$$file' '$(DESTDIR)$(man1dir)/$$inst'"; \
+	  $(INSTALL_DATA) "$$file" "$(DESTDIR)$(man1dir)/$$inst"; \
+	done
+uninstall-man1:
+	@$(NORMAL_UNINSTALL)
+	@list='$(man1_MANS) $(dist_man1_MANS) $(nodist_man1_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.1*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    1*) ;; \
+	    *) ext='1' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " rm -f '$(DESTDIR)$(man1dir)/$$inst'"; \
+	  rm -f "$(DESTDIR)$(man1dir)/$$inst"; \
+	done
+install-man3: $(man3_MANS) $(man_MANS)
+	@$(NORMAL_INSTALL)
+	test -z "$(man3dir)" || $(mkdir_p) "$(DESTDIR)$(man3dir)"
+	@list='$(man3_MANS) $(dist_man3_MANS) $(nodist_man3_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.3*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  if test -f $(srcdir)/$$i; then file=$(srcdir)/$$i; \
+	  else file=$$i; fi; \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    3*) ;; \
+	    *) ext='3' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " $(INSTALL_DATA) '$$file' '$(DESTDIR)$(man3dir)/$$inst'"; \
+	  $(INSTALL_DATA) "$$file" "$(DESTDIR)$(man3dir)/$$inst"; \
+	done
+uninstall-man3:
+	@$(NORMAL_UNINSTALL)
+	@list='$(man3_MANS) $(dist_man3_MANS) $(nodist_man3_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.3*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    3*) ;; \
+	    *) ext='3' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " rm -f '$(DESTDIR)$(man3dir)/$$inst'"; \
+	  rm -f "$(DESTDIR)$(man3dir)/$$inst"; \
+	done
+install-man5: $(man5_MANS) $(man_MANS)
+	@$(NORMAL_INSTALL)
+	test -z "$(man5dir)" || $(mkdir_p) "$(DESTDIR)$(man5dir)"
+	@list='$(man5_MANS) $(dist_man5_MANS) $(nodist_man5_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.5*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  if test -f $(srcdir)/$$i; then file=$(srcdir)/$$i; \
+	  else file=$$i; fi; \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    5*) ;; \
+	    *) ext='5' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " $(INSTALL_DATA) '$$file' '$(DESTDIR)$(man5dir)/$$inst'"; \
+	  $(INSTALL_DATA) "$$file" "$(DESTDIR)$(man5dir)/$$inst"; \
+	done
+uninstall-man5:
+	@$(NORMAL_UNINSTALL)
+	@list='$(man5_MANS) $(dist_man5_MANS) $(nodist_man5_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.5*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    5*) ;; \
+	    *) ext='5' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " rm -f '$(DESTDIR)$(man5dir)/$$inst'"; \
+	  rm -f "$(DESTDIR)$(man5dir)/$$inst"; \
+	done
+install-man7: $(man7_MANS) $(man_MANS)
+	@$(NORMAL_INSTALL)
+	test -z "$(man7dir)" || $(mkdir_p) "$(DESTDIR)$(man7dir)"
+	@list='$(man7_MANS) $(dist_man7_MANS) $(nodist_man7_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.7*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  if test -f $(srcdir)/$$i; then file=$(srcdir)/$$i; \
+	  else file=$$i; fi; \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    7*) ;; \
+	    *) ext='7' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " $(INSTALL_DATA) '$$file' '$(DESTDIR)$(man7dir)/$$inst'"; \
+	  $(INSTALL_DATA) "$$file" "$(DESTDIR)$(man7dir)/$$inst"; \
+	done
+uninstall-man7:
+	@$(NORMAL_UNINSTALL)
+	@list='$(man7_MANS) $(dist_man7_MANS) $(nodist_man7_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.7*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    7*) ;; \
+	    *) ext='7' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " rm -f '$(DESTDIR)$(man7dir)/$$inst'"; \
+	  rm -f "$(DESTDIR)$(man7dir)/$$inst"; \
+	done
+tags: TAGS
+TAGS:
+
+ctags: CTAGS
+CTAGS:
+
+
+distdir: $(DISTFILES)
+	@srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; \
+	topsrcdirstrip=`echo "$(top_srcdir)" | sed 's|.|.|g'`; \
+	list='$(DISTFILES)'; for file in $$list; do \
+	  case $$file in \
+	    $(srcdir)/*) file=`echo "$$file" | sed "s|^$$srcdirstrip/||"`;; \
+	    $(top_srcdir)/*) file=`echo "$$file" | sed "s|^$$topsrcdirstrip/|$(top_builddir)/|"`;; \
+	  esac; \
+	  if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \
+	  dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \
+	  if test "$$dir" != "$$file" && test "$$dir" != "."; then \
+	    dir="/$$dir"; \
+	    $(mkdir_p) "$(distdir)$$dir"; \
+	  else \
+	    dir=''; \
+	  fi; \
+	  if test -d $$d/$$file; then \
+	    if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \
+	      cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \
+	    fi; \
+	    cp -pR $$d/$$file $(distdir)$$dir || exit 1; \
+	  else \
+	    test -f $(distdir)/$$file \
+	    || cp -p $$d/$$file $(distdir)/$$file \
+	    || exit 1; \
+	  fi; \
+	done
+check-am: all-am
+check: check-am
+all-am: Makefile $(MANS)
+installdirs:
+	for dir in "$(DESTDIR)$(man1dir)" "$(DESTDIR)$(man3dir)" "$(DESTDIR)$(man5dir)" "$(DESTDIR)$(man7dir)"; do \
+	  test -z "$$dir" || $(mkdir_p) "$$dir"; \
+	done
+install: install-am
+install-exec: install-exec-am
+install-data: install-data-am
+uninstall: uninstall-am
+
+install-am: all-am
+	@$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am
+
+installcheck: installcheck-am
+install-strip:
+	$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
+	  install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
+	  `test -z '$(STRIP)' || \
+	    echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
+mostlyclean-generic:
+
+clean-generic:
+
+distclean-generic:
+	-test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES)
+
+maintainer-clean-generic:
+	@echo "This command is intended for maintainers to use"
+	@echo "it deletes files that may require special tools to rebuild."
+clean: clean-am
+
+clean-am: clean-generic mostlyclean-am
+
+distclean: distclean-am
+	-rm -f Makefile
+distclean-am: clean-am distclean-generic
+
+dvi: dvi-am
+
+dvi-am:
+
+html: html-am
+
+info: info-am
+
+info-am:
+
+install-data-am: install-man
+
+install-exec-am:
+
+install-info: install-info-am
+
+install-man: install-man1 install-man3 install-man5 install-man7
+
+installcheck-am:
+
+maintainer-clean: maintainer-clean-am
+	-rm -f Makefile
+maintainer-clean-am: distclean-am maintainer-clean-generic
+
+mostlyclean: mostlyclean-am
+
+mostlyclean-am: mostlyclean-generic
+
+pdf: pdf-am
+
+pdf-am:
+
+ps: ps-am
+
+ps-am:
+
+uninstall-am: uninstall-info-am uninstall-man
+
+uninstall-man: uninstall-man1 uninstall-man3 uninstall-man5 \
+	uninstall-man7
+
+.PHONY: all all-am check check-am clean clean-generic distclean \
+	distclean-generic distdir dvi dvi-am html html-am info info-am \
+	install install-am install-data install-data-am install-exec \
+	install-exec-am install-info install-info-am install-man \
+	install-man1 install-man3 install-man5 install-man7 \
+	install-strip installcheck installcheck-am installdirs \
+	maintainer-clean maintainer-clean-generic mostlyclean \
+	mostlyclean-generic pdf pdf-am ps ps-am uninstall uninstall-am \
+	uninstall-info-am uninstall-man uninstall-man1 uninstall-man3 \
+	uninstall-man5 uninstall-man7
+
+# Tell versions [3.59,3.63) of GNU make to not export all variables.
+# Otherwise a system limit (for SysV at least) may be exceeded.
+.NOEXPORT:

corpora/en/wordnet/doc/man/Makefile.am

@@ -0,0 +1 @@
+man_MANS = binsrch.3 cntlist.5 grind.1 lexnames.5 morph.3 morphy.7 senseidx.5 uniqbeg.7 wn.1 wnb.1 wndb.5 wngloss.7 wngroups.7 wninput.5 wnintro.1 wnintro.3 wnintro.5 wnintro.7 wnlicens.7 wnpkgs.7 wnsearch.3 wnstats.7 wnutil.3

corpora/en/wordnet/doc/man/Makefile.in

@@ -0,0 +1,478 @@
+# Makefile.in generated by automake 1.9 from Makefile.am.
+# @configure_input@
+
+# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
+# 2003, 2004  Free Software Foundation, Inc.
+# This Makefile.in is free software; the Free Software Foundation
+# gives unlimited permission to copy and/or distribute it,
+# with or without modifications, as long as this notice is preserved.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
+# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+# PARTICULAR PURPOSE.
+
+@SET_MAKE@
+srcdir = @srcdir@
+top_srcdir = @top_srcdir@
+VPATH = @srcdir@
+pkgdatadir = $(datadir)/@PACKAGE@
+pkglibdir = $(libdir)/@PACKAGE@
+pkgincludedir = $(includedir)/@PACKAGE@
+top_builddir = ../..
+am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd
+INSTALL = @INSTALL@
+install_sh_DATA = $(install_sh) -c -m 644
+install_sh_PROGRAM = $(install_sh) -c
+install_sh_SCRIPT = $(install_sh) -c
+INSTALL_HEADER = $(INSTALL_DATA)
+transform = $(program_transform_name)
+NORMAL_INSTALL = :
+PRE_INSTALL = :
+POST_INSTALL = :
+NORMAL_UNINSTALL = :
+PRE_UNINSTALL = :
+POST_UNINSTALL = :
+subdir = doc/man
+DIST_COMMON = $(srcdir)/Makefile.am $(srcdir)/Makefile.in
+ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
+am__aclocal_m4_deps = $(top_srcdir)/acinclude.m4 \
+	$(top_srcdir)/configure.ac
+am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
+	$(ACLOCAL_M4)
+mkinstalldirs = $(install_sh) -d
+CONFIG_HEADER = $(top_builddir)/config.h
+CONFIG_CLEAN_FILES =
+SOURCES =
+DIST_SOURCES =
+man1dir = $(mandir)/man1
+am__installdirs = "$(DESTDIR)$(man1dir)" "$(DESTDIR)$(man3dir)" \
+	"$(DESTDIR)$(man5dir)" "$(DESTDIR)$(man7dir)"
+man3dir = $(mandir)/man3
+man5dir = $(mandir)/man5
+man7dir = $(mandir)/man7
+NROFF = nroff
+MANS = $(man_MANS)
+DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
+ACLOCAL = @ACLOCAL@
+AMDEP_FALSE = @AMDEP_FALSE@
+AMDEP_TRUE = @AMDEP_TRUE@
+AMTAR = @AMTAR@
+AUTOCONF = @AUTOCONF@
+AUTOHEADER = @AUTOHEADER@
+AUTOMAKE = @AUTOMAKE@
+AWK = @AWK@
+CC = @CC@
+CCDEPMODE = @CCDEPMODE@
+CFLAGS = @CFLAGS@
+CPP = @CPP@
+CPPFLAGS = @CPPFLAGS@
+CYGPATH_W = @CYGPATH_W@
+DEFS = @DEFS@
+DEPDIR = @DEPDIR@
+ECHO_C = @ECHO_C@
+ECHO_N = @ECHO_N@
+ECHO_T = @ECHO_T@
+EGREP = @EGREP@
+EXEEXT = @EXEEXT@
+INSTALL_DATA = @INSTALL_DATA@
+INSTALL_PROGRAM = @INSTALL_PROGRAM@
+INSTALL_SCRIPT = @INSTALL_SCRIPT@
+INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@
+LDFLAGS = @LDFLAGS@
+LIBOBJS = @LIBOBJS@
+LIBS = @LIBS@
+LTLIBOBJS = @LTLIBOBJS@
+MAKEINFO = @MAKEINFO@
+OBJEXT = @OBJEXT@
+PACKAGE = @PACKAGE@
+PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@
+PACKAGE_NAME = @PACKAGE_NAME@
+PACKAGE_STRING = @PACKAGE_STRING@
+PACKAGE_TARNAME = @PACKAGE_TARNAME@
+PACKAGE_VERSION = @PACKAGE_VERSION@
+PATH_SEPARATOR = @PATH_SEPARATOR@
+RANLIB = @RANLIB@
+SET_MAKE = @SET_MAKE@
+SHELL = @SHELL@
+STRIP = @STRIP@
+TCL_INCLUDE_SPEC = @TCL_INCLUDE_SPEC@
+TCL_LIB_SPEC = @TCL_LIB_SPEC@
+TK_LIBS = @TK_LIBS@
+TK_LIB_SPEC = @TK_LIB_SPEC@
+TK_PREFIX = @TK_PREFIX@
+TK_XINCLUDES = @TK_XINCLUDES@
+VERSION = @VERSION@
+ac_ct_CC = @ac_ct_CC@
+ac_ct_RANLIB = @ac_ct_RANLIB@
+ac_ct_STRIP = @ac_ct_STRIP@
+ac_prefix = @ac_prefix@
+am__fastdepCC_FALSE = @am__fastdepCC_FALSE@
+am__fastdepCC_TRUE = @am__fastdepCC_TRUE@
+am__include = @am__include@
+am__leading_dot = @am__leading_dot@
+am__quote = @am__quote@
+am__tar = @am__tar@
+am__untar = @am__untar@
+bindir = @bindir@
+build_alias = @build_alias@
+datadir = @datadir@
+exec_prefix = @exec_prefix@
+host_alias = @host_alias@
+includedir = @includedir@
+infodir = @infodir@
+install_sh = @install_sh@
+libdir = @libdir@
+libexecdir = @libexecdir@
+localstatedir = @localstatedir@
+mandir = @mandir@
+mkdir_p = @mkdir_p@
+oldincludedir = @oldincludedir@
+prefix = @prefix@
+program_transform_name = @program_transform_name@
+sbindir = @sbindir@
+sharedstatedir = @sharedstatedir@
+sysconfdir = @sysconfdir@
+target_alias = @target_alias@
+man_MANS = binsrch.3 cntlist.5 grind.1 lexnames.5 morph.3 morphy.7 senseidx.5 uniqbeg.7 wn.1 wnb.1 wndb.5 wngloss.7 wngroups.7 wninput.5 wnintro.1 wnintro.3 wnintro.5 wnintro.7 wnlicens.7 wnpkgs.7 wnsearch.3 wnstats.7 wnutil.3
+all: all-am
+
+.SUFFIXES:
+$(srcdir)/Makefile.in:  $(srcdir)/Makefile.am  $(am__configure_deps)
+	@for dep in $?; do \
+	  case '$(am__configure_deps)' in \
+	    *$$dep*) \
+	      cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh \
+		&& exit 0; \
+	      exit 1;; \
+	  esac; \
+	done; \
+	echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu  doc/man/Makefile'; \
+	cd $(top_srcdir) && \
+	  $(AUTOMAKE) --gnu  doc/man/Makefile
+.PRECIOUS: Makefile
+Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status
+	@case '$?' in \
+	  *config.status*) \
+	    cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \
+	  *) \
+	    echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)'; \
+	    cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \
+	esac;
+
+$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+
+$(top_srcdir)/configure:  $(am__configure_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+$(ACLOCAL_M4):  $(am__aclocal_m4_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+uninstall-info-am:
+install-man1: $(man1_MANS) $(man_MANS)
+	@$(NORMAL_INSTALL)
+	test -z "$(man1dir)" || $(mkdir_p) "$(DESTDIR)$(man1dir)"
+	@list='$(man1_MANS) $(dist_man1_MANS) $(nodist_man1_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.1*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  if test -f $(srcdir)/$$i; then file=$(srcdir)/$$i; \
+	  else file=$$i; fi; \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    1*) ;; \
+	    *) ext='1' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " $(INSTALL_DATA) '$$file' '$(DESTDIR)$(man1dir)/$$inst'"; \
+	  $(INSTALL_DATA) "$$file" "$(DESTDIR)$(man1dir)/$$inst"; \
+	done
+uninstall-man1:
+	@$(NORMAL_UNINSTALL)
+	@list='$(man1_MANS) $(dist_man1_MANS) $(nodist_man1_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.1*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    1*) ;; \
+	    *) ext='1' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " rm -f '$(DESTDIR)$(man1dir)/$$inst'"; \
+	  rm -f "$(DESTDIR)$(man1dir)/$$inst"; \
+	done
+install-man3: $(man3_MANS) $(man_MANS)
+	@$(NORMAL_INSTALL)
+	test -z "$(man3dir)" || $(mkdir_p) "$(DESTDIR)$(man3dir)"
+	@list='$(man3_MANS) $(dist_man3_MANS) $(nodist_man3_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.3*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  if test -f $(srcdir)/$$i; then file=$(srcdir)/$$i; \
+	  else file=$$i; fi; \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    3*) ;; \
+	    *) ext='3' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " $(INSTALL_DATA) '$$file' '$(DESTDIR)$(man3dir)/$$inst'"; \
+	  $(INSTALL_DATA) "$$file" "$(DESTDIR)$(man3dir)/$$inst"; \
+	done
+uninstall-man3:
+	@$(NORMAL_UNINSTALL)
+	@list='$(man3_MANS) $(dist_man3_MANS) $(nodist_man3_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.3*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    3*) ;; \
+	    *) ext='3' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " rm -f '$(DESTDIR)$(man3dir)/$$inst'"; \
+	  rm -f "$(DESTDIR)$(man3dir)/$$inst"; \
+	done
+install-man5: $(man5_MANS) $(man_MANS)
+	@$(NORMAL_INSTALL)
+	test -z "$(man5dir)" || $(mkdir_p) "$(DESTDIR)$(man5dir)"
+	@list='$(man5_MANS) $(dist_man5_MANS) $(nodist_man5_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.5*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  if test -f $(srcdir)/$$i; then file=$(srcdir)/$$i; \
+	  else file=$$i; fi; \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    5*) ;; \
+	    *) ext='5' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " $(INSTALL_DATA) '$$file' '$(DESTDIR)$(man5dir)/$$inst'"; \
+	  $(INSTALL_DATA) "$$file" "$(DESTDIR)$(man5dir)/$$inst"; \
+	done
+uninstall-man5:
+	@$(NORMAL_UNINSTALL)
+	@list='$(man5_MANS) $(dist_man5_MANS) $(nodist_man5_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.5*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    5*) ;; \
+	    *) ext='5' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " rm -f '$(DESTDIR)$(man5dir)/$$inst'"; \
+	  rm -f "$(DESTDIR)$(man5dir)/$$inst"; \
+	done
+install-man7: $(man7_MANS) $(man_MANS)
+	@$(NORMAL_INSTALL)
+	test -z "$(man7dir)" || $(mkdir_p) "$(DESTDIR)$(man7dir)"
+	@list='$(man7_MANS) $(dist_man7_MANS) $(nodist_man7_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.7*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  if test -f $(srcdir)/$$i; then file=$(srcdir)/$$i; \
+	  else file=$$i; fi; \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    7*) ;; \
+	    *) ext='7' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " $(INSTALL_DATA) '$$file' '$(DESTDIR)$(man7dir)/$$inst'"; \
+	  $(INSTALL_DATA) "$$file" "$(DESTDIR)$(man7dir)/$$inst"; \
+	done
+uninstall-man7:
+	@$(NORMAL_UNINSTALL)
+	@list='$(man7_MANS) $(dist_man7_MANS) $(nodist_man7_MANS)'; \
+	l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \
+	for i in $$l2; do \
+	  case "$$i" in \
+	    *.7*) list="$$list $$i" ;; \
+	  esac; \
+	done; \
+	for i in $$list; do \
+	  ext=`echo $$i | sed -e 's/^.*\\.//'`; \
+	  case "$$ext" in \
+	    7*) ;; \
+	    *) ext='7' ;; \
+	  esac; \
+	  inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \
+	  inst=`echo $$inst | sed -e 's/^.*\///'`; \
+	  inst=`echo $$inst | sed '$(transform)'`.$$ext; \
+	  echo " rm -f '$(DESTDIR)$(man7dir)/$$inst'"; \
+	  rm -f "$(DESTDIR)$(man7dir)/$$inst"; \
+	done
+tags: TAGS
+TAGS:
+
+ctags: CTAGS
+CTAGS:
+
+
+distdir: $(DISTFILES)
+	@srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; \
+	topsrcdirstrip=`echo "$(top_srcdir)" | sed 's|.|.|g'`; \
+	list='$(DISTFILES)'; for file in $$list; do \
+	  case $$file in \
+	    $(srcdir)/*) file=`echo "$$file" | sed "s|^$$srcdirstrip/||"`;; \
+	    $(top_srcdir)/*) file=`echo "$$file" | sed "s|^$$topsrcdirstrip/|$(top_builddir)/|"`;; \
+	  esac; \
+	  if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \
+	  dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \
+	  if test "$$dir" != "$$file" && test "$$dir" != "."; then \
+	    dir="/$$dir"; \
+	    $(mkdir_p) "$(distdir)$$dir"; \
+	  else \
+	    dir=''; \
+	  fi; \
+	  if test -d $$d/$$file; then \
+	    if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \
+	      cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \
+	    fi; \
+	    cp -pR $$d/$$file $(distdir)$$dir || exit 1; \
+	  else \
+	    test -f $(distdir)/$$file \
+	    || cp -p $$d/$$file $(distdir)/$$file \
+	    || exit 1; \
+	  fi; \
+	done
+check-am: all-am
+check: check-am
+all-am: Makefile $(MANS)
+installdirs:
+	for dir in "$(DESTDIR)$(man1dir)" "$(DESTDIR)$(man3dir)" "$(DESTDIR)$(man5dir)" "$(DESTDIR)$(man7dir)"; do \
+	  test -z "$$dir" || $(mkdir_p) "$$dir"; \
+	done
+install: install-am
+install-exec: install-exec-am
+install-data: install-data-am
+uninstall: uninstall-am
+
+install-am: all-am
+	@$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am
+
+installcheck: installcheck-am
+install-strip:
+	$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
+	  install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
+	  `test -z '$(STRIP)' || \
+	    echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
+mostlyclean-generic:
+
+clean-generic:
+
+distclean-generic:
+	-test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES)
+
+maintainer-clean-generic:
+	@echo "This command is intended for maintainers to use"
+	@echo "it deletes files that may require special tools to rebuild."
+clean: clean-am
+
+clean-am: clean-generic mostlyclean-am
+
+distclean: distclean-am
+	-rm -f Makefile
+distclean-am: clean-am distclean-generic
+
+dvi: dvi-am
+
+dvi-am:
+
+html: html-am
+
+info: info-am
+
+info-am:
+
+install-data-am: install-man
+
+install-exec-am:
+
+install-info: install-info-am
+
+install-man: install-man1 install-man3 install-man5 install-man7
+
+installcheck-am:
+
+maintainer-clean: maintainer-clean-am
+	-rm -f Makefile
+maintainer-clean-am: distclean-am maintainer-clean-generic
+
+mostlyclean: mostlyclean-am
+
+mostlyclean-am: mostlyclean-generic
+
+pdf: pdf-am
+
+pdf-am:
+
+ps: ps-am
+
+ps-am:
+
+uninstall-am: uninstall-info-am uninstall-man
+
+uninstall-man: uninstall-man1 uninstall-man3 uninstall-man5 \
+	uninstall-man7
+
+.PHONY: all all-am check check-am clean clean-generic distclean \
+	distclean-generic distdir dvi dvi-am html html-am info info-am \
+	install install-am install-data install-data-am install-exec \
+	install-exec-am install-info install-info-am install-man \
+	install-man1 install-man3 install-man5 install-man7 \
+	install-strip installcheck installcheck-am installdirs \
+	maintainer-clean maintainer-clean-generic mostlyclean \
+	mostlyclean-generic pdf pdf-am ps ps-am uninstall uninstall-am \
+	uninstall-info-am uninstall-man uninstall-man1 uninstall-man3 \
+	uninstall-man5 uninstall-man7
+
+# Tell versions [3.59,3.63) of GNU make to not export all variables.
+# Otherwise a system limit (for SysV at least) may be exceeded.
+.NOEXPORT: