spaCy/spacy/lang/fr/syntax_iterators.py

57 lines
1.7 KiB
Python
Raw Normal View History

# coding: utf8
from __future__ import unicode_literals
from ...symbols import NOUN, PROPN, PRON
from ...errors import Errors
def noun_chunks(obj):
"""
Detect base noun phrases from a dependency parse. Works on both Doc and Span.
"""
labels = [
"nsubj",
"nsubj:pass",
"obj",
"iobj",
"ROOT",
"appos",
"nmod",
"nmod:poss",
]
doc = obj.doc # Ensure works on both Doc and Span.
if not doc.is_parsed:
raise ValueError(Errors.E029)
np_deps = [doc.vocab.strings[label] for label in labels]
conj = doc.vocab.strings.add("conj")
np_label = doc.vocab.strings.add("NP")
seen = set()
for i, word in enumerate(obj):
if word.pos not in (NOUN, PROPN, PRON):
continue
# Prevent nested chunks from being produced
if word.i in seen:
continue
if word.dep in np_deps:
2020-05-20 22:17:28 +00:00
w_range = range(word.left_edge.i, word.right_edge.i + 1)
if any(j in seen for j in w_range):
continue
2020-05-20 22:17:28 +00:00
seen.update(j for j in w_range)
yield word.left_edge.i, word.right_edge.i + 1, np_label
elif 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:
2020-05-20 22:17:28 +00:00
w_range = range(word.left_edge.i, word.right_edge.i + 1)
if any(j in seen for j in w_range):
continue
2020-05-20 22:17:28 +00:00
seen.update(j for j in w_range)
yield word.left_edge.i, word.right_edge.i + 1, np_label
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}