explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-05 13:43:24 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Fix Issue #365: Error introduced during noun phrase chunking, due to use of corrected PRON/PROPN/etc tags.

Browse Source
This commit is contained in:
Matthew Honnibal 2016-05-06 00:21:05 +02:00
parent 41342ca79b
commit bb94022975
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/syntax/iterators.pyx
View File

@ -1,4 +1,4 @@
from spacy.parts_of_speech cimport NOUN from spacy.parts_of_speech cimport NOUN, PROPN, PRON
def english_noun_chunks(doc): def english_noun_chunks(doc):
@ -9,7 +9,7 @@ def english_noun_chunks(doc):
np_label = doc.vocab.strings['NP'] np_label = doc.vocab.strings['NP']
for i in range(len(doc)): for i in range(len(doc)):
word = doc[i] word = doc[i]
if word.pos == NOUN and word.dep in np_deps: if word.pos in (NOUN, PROPN, PRON) and word.dep in np_deps:
yield word.left_edge.i, word.i+1, np_label yield word.left_edge.i, word.i+1, np_label
elif word.pos == NOUN and word.dep == conj: elif word.pos == NOUN and word.dep == conj:
head = word.head head = word.head
@ -36,7 +36,7 @@ def german_noun_chunks(doc):
for i, word in enumerate(doc): for i, word in enumerate(doc):
if i < rbracket: if i < rbracket:
continue continue
if word.pos == NOUN and word.dep in np_deps: if word.pos == (NOUN, PROPN, PRON) and word.dep in np_deps:
rbracket = word.i+1 rbracket = word.i+1
# try to extend the span to the right # try to extend the span to the right
# to capture close apposition/measurement constructions # to capture close apposition/measurement constructions