Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Allow German noun chunks to work on Span 

Update the German noun chunks iterator, so that it also works on Span objects.
This commit is contained in:
Matthew Honnibal 2016-11-24 23:30:15 +11:00 committed by GitHub
parent 3e3bda142d
commit b8c4f5ea76
1 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/syntax/iterators.pyx
View File

@ -2,9 +2,11 @@ from spacy.parts_of_speech cimport NOUN, PROPN, PRON
def english_noun_chunks(obj): def english_noun_chunks(obj):
'''Detect base noun phrases from a dependency parse.
Works on both Doc and Span.'''
labels = ['nsubj', 'dobj', 'nsubjpass', 'pcomp', 'pobj', labels = ['nsubj', 'dobj', 'nsubjpass', 'pcomp', 'pobj',
'attr', 'ROOT', 'root'] 'attr', 'ROOT', 'root']
doc = obj.doc 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']
@ -26,14 +28,15 @@ def english_noun_chunks(obj):
# extended to the right of the NOUN # extended to the right of the NOUN
# example: "eine Tasse Tee" (a cup (of) tea) returns "eine Tasse Tee" and not # example: "eine Tasse Tee" (a cup (of) tea) returns "eine Tasse Tee" and not
# 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(obj):
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']
doc = obj.doc # Ensure works on both Doc and Span.
np_label = doc.vocab.strings['NP'] np_label = doc.vocab.strings['NP']
np_deps = set(doc.vocab.strings[label] for label in labels) np_deps = set(doc.vocab.strings[label] for label in labels)
close_app = doc.vocab.strings['nk'] close_app = doc.vocab.strings['nk']
rbracket = 0 rbracket = 0
for i, word in enumerate(doc): for i, word in enumerate(obj):
if i < rbracket: if i < rbracket:
continue continue
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: