spaCy/spacy/lang/id/syntax_iterators.py

42 lines
1.5 KiB
Python
Raw Normal View History

from typing import Union, Iterator
2017-07-27 06:51:34 +03:00
from ...symbols import NOUN, PROPN, PRON
from ...errors import Errors
from ...tokens import Doc, Span
2017-07-27 06:51:34 +03:00
def noun_chunks(doclike: Union[Doc, Span]) -> Iterator[Span]:
2017-07-27 06:51:34 +03:00
"""
Detect base noun phrases from a dependency parse. Works on both Doc and Span.
"""
# fmt: off
labels = ["nsubj", "nsubj:pass", "obj", "iobj", "ROOT", "appos", "nmod", "nmod:poss"]
# fmt: on
doc = doclike.doc # Ensure works on both Doc and Span.
if not doc.is_parsed:
raise ValueError(Errors.E029)
2017-07-27 06:51:34 +03:00
np_deps = [doc.vocab.strings[label] for label in labels]
conj = doc.vocab.strings.add("conj")
np_label = doc.vocab.strings.add("NP")
prev_end = -1
for i, word in enumerate(doclike):
2017-07-27 06:51:34 +03:00
if word.pos not in (NOUN, PROPN, PRON):
continue
# Prevent nested chunks from being produced
if word.left_edge.i <= prev_end:
2017-07-27 06:51:34 +03:00
continue
if word.dep in np_deps:
prev_end = word.right_edge.i
yield word.left_edge.i, word.right_edge.i + 1, np_label
2017-07-27 06:51:34 +03:00
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:
prev_end = word.right_edge.i
yield word.left_edge.i, word.right_edge.i + 1, np_label
2017-07-27 06:51:34 +03:00
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}