mirror of https://github.com/explosion/spaCy.git
47 lines
1.9 KiB
Cython
47 lines
1.9 KiB
Cython
from spacy.parts_of_speech cimport NOUN
|
|
|
|
|
|
def english_noun_chunks(doc):
|
|
labels = ['nsubj', 'dobj', 'nsubjpass', 'pcomp', 'pobj',
|
|
'attr', 'root']
|
|
np_deps = [doc.vocab.strings[label] for label in labels]
|
|
conj = doc.vocab.strings['conj']
|
|
np_label = doc.vocab.strings['NP']
|
|
for i in range(len(doc)):
|
|
word = doc[i]
|
|
if word.pos == NOUN and word.dep in np_deps:
|
|
yield word.left_edge.i, word.i+1, np_label
|
|
elif word.pos == NOUN and word.dep == conj:
|
|
head = word.head
|
|
while head.dep == conj and head.head.i < head.i:
|
|
head = head.head
|
|
# If the head is an NP, and we're coordinated to it, we're an NP
|
|
if head.dep in np_deps:
|
|
yield word.left_edge.i, word.i+1, np_label
|
|
|
|
|
|
# this iterator extracts spans headed by NOUNs starting from the left-most
|
|
# syntactic dependent until the NOUN itself
|
|
# for close apposition and measurement construction, the span is sometimes
|
|
# extended to the right of the NOUN
|
|
# example: "eine Tasse Tee" (a cup (of) tea) returns "eine Tasse Tee" and not
|
|
# just "eine Tasse", same for "das Thema Familie"
|
|
def german_noun_chunks(doc):
|
|
labels = ['sb', 'oa', 'da', 'nk', 'mo', 'ag', 'root', 'cj', 'pd', 'og', 'app']
|
|
np_label = doc.vocab.strings['NP']
|
|
np_deps = set(doc.vocab.strings[label] for label in labels)
|
|
close_app = doc.vocab.strings['nk']
|
|
|
|
for word in doc:
|
|
if word.pos == NOUN and word.dep in np_deps:
|
|
rbracket = word.i+1
|
|
# try to extend the span to the right
|
|
# to capture close apposition/measurement constructions
|
|
for rdep in doc[word.i].rights:
|
|
if rdep.pos == NOUN and rdep.dep == close_app:
|
|
rbracket = rdep.i+1
|
|
yield word.l_edge, rbracket, np_label
|
|
|
|
|
|
CHUNKERS = {'en': english_noun_chunks, 'de': german_noun_chunks}
|