explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-27 09:44:36 +03:00
Code Issues Packages Projects Releases Wiki Activity

Changes to iterators.pyx for new StringStore scheme

Browse Source
This commit is contained in:
Matthew Honnibal 2016-09-30 19:57:49 +02:00
parent 95f8cfd745
commit 4f794b215a
1 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
spacy/syntax/iterators.pyx
View File

@ -4,9 +4,9 @@ from spacy.parts_of_speech cimport NOUN, PROPN, PRON
def english_noun_chunks(doc): def english_noun_chunks(doc):
labels = ['nsubj', 'dobj', 'nsubjpass', 'pcomp', 'pobj', labels = ['nsubj', 'dobj', 'nsubjpass', 'pcomp', 'pobj',
'attr', 'ROOT', 'root'] 'attr', 'ROOT', 'root']
np_deps = [doc.vocab.strings[label] for label in labels] np_deps = [doc.vocab.strings.intern(label) for label in labels]
conj = doc.vocab.strings['conj'] conj = doc.vocab.strings.intern('conj')
np_label = doc.vocab.strings['NP'] np_label = doc.vocab.strings.intern('NP')
for i, word in enumerate(doc): for i, word in enumerate(doc):
if word.pos in (NOUN, PROPN, PRON) 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
@ -27,10 +27,9 @@ def english_noun_chunks(doc):
# just "eine Tasse", same for "das Thema Familie" # just "eine Tasse", same for "das Thema Familie"
def german_noun_chunks(doc): def german_noun_chunks(doc):
labels = ['sb', 'oa', 'da', 'nk', 'mo', 'ag', 'ROOT', 'root', 'cj', 'pd', 'og', 'app'] labels = ['sb', 'oa', 'da', 'nk', 'mo', 'ag', 'ROOT', 'root', 'cj', 'pd', 'og', 'app']
np_label = doc.vocab.strings['NP'] np_label = doc.vocab.strings.intern('NP')
np_deps = set(doc.vocab.strings[label] for label in labels) np_deps = set(doc.vocab.strings.intern(label) for label in labels)
close_app = doc.vocab.strings['nk'] close_app = doc.vocab.strings.intern('nk')
rbracket = 0 rbracket = 0
for i, word in enumerate(doc): for i, word in enumerate(doc):
if i < rbracket: if i < rbracket: