explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-14 13:47:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Fix init_model to read supersenses from wordnet, not pre-computed supersenses file

Browse Source
This commit is contained in:
Matthew Honnibal 2015-07-03 13:28:39 +02:00
parent b977d60bf4
commit ff1f9fe246
1 changed files with 9 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
bin/init_model.py
View File

@ -28,7 +28,7 @@ from spacy.en.lemmatizer import Lemmatizer
from spacy.vocab import Vocab from spacy.vocab import Vocab
from spacy.vocab import write_binary_vectors from spacy.vocab import write_binary_vectors
from spacy.parts_of_speech import NOUN, VERB, ADJ from spacy.parts_of_speech import NOUN, VERB, ADJ, ADV
import spacy.senses import spacy.senses
@ -80,19 +80,14 @@ def _read_probs(loc):
def _read_senses(loc): def _read_senses(loc):
lexicon = defaultdict(lambda: defaultdict(list)) lexicon = defaultdict(lambda: defaultdict(list))
sense_names = dict((s, i) for i, s in enumerate(spacy.senses.STRINGS)) pos_tags = [None, NOUN, VERB, ADJ, ADV, None]
pos_ids = {'noun': NOUN, 'verb': VERB, 'adjective': ADJ}
for line in codecs.open(str(loc), 'r', 'utf8'): for line in codecs.open(str(loc), 'r', 'utf8'):
sense_strings = line.split() sense_key, synset_offset, sense_number, tag_cnt = line.split()
word = sense_strings.pop(0) lemma, lex_sense = sense_key.split('%')
for sense in sense_strings: ss_type, lex_filenum, lex_id, head_word, head_id = lex_sense.split(':')
pos, sense = sense[3:].split('.') pos = pos_tags[int(ss_type)]
if pos[0].upper() == 'A': if pos is not None:
continue lexicon[lemma][pos].append(int(lex_filenum))
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 return lexicon
@ -105,7 +100,7 @@ def setup_vocab(src_dir, dst_dir):
write_binary_vectors(str(vectors_src), str(dst_dir / 'vec.bin')) write_binary_vectors(str(vectors_src), str(dst_dir / 'vec.bin'))
vocab = Vocab(data_dir=None, get_lex_props=get_lex_props) vocab = Vocab(data_dir=None, get_lex_props=get_lex_props)
clusters = _read_clusters(src_dir / 'clusters.txt') clusters = _read_clusters(src_dir / 'clusters.txt')
senses = _read_senses(src_dir / 'supersenses.txt') senses = _read_senses(src_dir / 'wordnet' / 'index.sense')
probs = _read_probs(src_dir / 'words.sgt.prob') probs = _read_probs(src_dir / 'words.sgt.prob')
for word in set(clusters).union(set(senses)): for word in set(clusters).union(set(senses)):
if word not in probs: if word not in probs: