Add built-in factories for merge_entities and merge_noun_chunks

Allows adding those components to the pipeline out-of-the-box if they're defined in a model's meta.json. Also allows usage as nlp.add_pipe(nlp.create_pipe('merge_entities')).

spacy/language.py

@@ -17,6 +17,7 @@ from .vocab import Vocab
 from .lemmatizer import Lemmatizer
 from .pipeline import DependencyParser, Tensorizer, Tagger, EntityRecognizer
 from .pipeline import SimilarityHook, TextCategorizer, SentenceSegmenter
+from .pipeline import merge_noun_chunks, merge_entities
 from .compat import json_dumps, izip, basestring_
 from .gold import GoldParse
 from .scorer import Scorer
@@ -105,7 +106,9 @@ class Language(object):
         'similarity': lambda nlp, **cfg: SimilarityHook(nlp.vocab, **cfg),
         'textcat': lambda nlp, **cfg: TextCategorizer(nlp.vocab, **cfg),
         'sbd': lambda nlp, **cfg: SentenceSegmenter(nlp.vocab, **cfg),
-        'sentencizer': lambda nlp, **cfg: SentenceSegmenter(nlp.vocab, **cfg)
+        'sentencizer': lambda nlp, **cfg: SentenceSegmenter(nlp.vocab, **cfg),
+        'merge_noun_chunks': lambda nlp, **cfg: merge_noun_chunks,
+        'merge_entities': lambda nlp, **cfg: merge_entities
     }
 
     def __init__(self, vocab=True, make_doc=True, meta={}, **kwargs):

spacy/pipeline.pyx

@@ -69,6 +69,34 @@ class SentenceSegmenter(object):
             yield doc[start:len(doc)]
 
 
+def merge_noun_chunks(doc):
+    """Merge noun chunks into a single token.
+
+    doc (Doc): The Doc object.
+    RETURNS (Doc): The Doc object with merged noun chunks.
+    """
+    if not doc.is_parsed:
+        return
+    spans = [(np.start_char, np.end_char, np.root.tag, np.root.dep)
+             for np in doc.noun_chunks]
+    for start, end, tag, dep in spans:
+        doc.merge(start, end, tag=tag, dep=dep)
+    return doc
+
+
+def merge_entities(doc):
+    """Merge entities into a single token.
+
+    doc (Doc): The Doc object.
+    RETURNS (Doc): The Doc object with merged noun entities.
+    """
+    spans = [(e.start_char, e.end_char, e.root.tag, e.root.dep, e.label)
+             for e in doc.ents]
+    for start, end, tag, dep, ent_type in spans:
+        doc.merge(start, end, tag=tag, dep=dep, ent_type=ent_type)
+    return doc
+
+
 class Pipe(object):
     """This class is not instantiated directly. Components inherit from it, and
     it defines the interface that components should follow to function as

spacy/tests/pipeline/test_factories.py

@@ -0,0 +1,44 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+import pytest
+
+from ..util import get_doc
+from ...language import Language
+from ...tokens import Span
+from ... import util
+
+@pytest.fixture
+def doc(en_tokenizer):
+    text = 'I like New York in Autumn.'
+    heads = [1, 0, 1, -2, -3, -1, -5]
+    tags = ['PRP', 'IN', 'NNP', 'NNP', 'IN', 'NNP', '.']
+    pos = ['PRON', 'VERB', 'PROPN', 'PROPN', 'ADP', 'PROPN', 'PUNCT']
+    deps = ['ROOT', 'prep', 'compound', 'pobj', 'prep', 'pobj', 'punct']
+    tokens = en_tokenizer(text)
+    doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads,
+                  tags=tags, pos=pos, deps=deps)
+    doc.ents = [Span(doc, 2, 4, doc.vocab.strings['GPE'])]
+    doc.is_parsed = True
+    doc.is_tagged = True
+    return doc
+
+
+def test_factories_merge_noun_chunks(doc):
+    assert len(doc) == 7
+    nlp = Language()
+    merge_noun_chunks = nlp.create_pipe('merge_noun_chunks')
+    merge_noun_chunks(doc)
+    assert len(doc) == 6
+    assert doc[2].text == 'New York'
+
+
+def test_factories_merge_ents(doc):
+    assert len(doc) == 7
+    assert len(list(doc.ents)) == 1
+    nlp = Language()
+    merge_entities = nlp.create_pipe('merge_entities')
+    merge_entities(doc)
+    assert len(doc) == 6
+    assert len(list(doc.ents)) == 1
+    assert doc[2].text == 'New York'