explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-27 17:54:39 +03:00
Code Issues Packages Projects Releases Wiki Activity

Ensure noun chunks can't be nested. Closes #955

Browse Source
This commit is contained in:
Matthew Honnibal 2017-04-23 17:56:39 +02:00
parent c9ec24b257
commit 60703cede5
1 changed files with 11 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacy/syntax/iterators.pyx
View File

@ -10,15 +10,22 @@ def english_noun_chunks(obj):
Works on both Doc and Span. Works on both Doc and Span.
""" """
labels = ['nsubj', 'dobj', 'nsubjpass', 'pcomp', 'pobj', labels = ['nsubj', 'dobj', 'nsubjpass', 'pcomp', 'pobj',
'attr', 'ROOT', 'root'] 'attr', 'ROOT']
doc = obj.doc # Ensure works on both Doc and Span. doc = obj.doc # Ensure works on both Doc and Span.
np_deps = [doc.vocab.strings[label] for label in labels] np_deps = [doc.vocab.strings[label] for label in labels]
conj = doc.vocab.strings['conj'] conj = doc.vocab.strings['conj']
np_label = doc.vocab.strings['NP'] np_label = doc.vocab.strings['NP']
seen = set()
for i, word in enumerate(obj): for i, word in enumerate(obj):
if word.pos not in (NOUN, PROPN, PRON): if word.pos not in (NOUN, PROPN, PRON):
continue continue
# Prevent nested chunks from being produced
if word.i in seen:
continue
if word.dep in np_deps: if word.dep in np_deps:
if any(w.i in seen for w in word.subtree):
continue
seen.update(j for j in range(word.left_edge.i, word.i+1))
yield word.left_edge.i, word.i+1, np_label yield word.left_edge.i, word.i+1, np_label
elif word.dep == conj: elif word.dep == conj:
head = word.head head = word.head
@ -26,6 +33,9 @@ def english_noun_chunks(obj):
head = head.head head = head.head
# If the head is an NP, and we're coordinated to it, we're an NP # If the head is an NP, and we're coordinated to it, we're an NP
if head.dep in np_deps: if head.dep in np_deps:
if any(w.i in seen for w in word.subtree):
continue
seen.update(j for j in range(word.left_edge.i, word.i+1))
yield word.left_edge.i, word.i+1, np_label yield word.left_edge.i, word.i+1, np_label