mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-13 05:07:03 +03:00
e2b70df012
* Use isort with Black profile * isort all the things * Fix import cycles as a result of import sorting * Add DOCBIN_ALL_ATTRS type definition * Add isort to requirements * Remove isort from build dependencies check * Typo
59 lines
1.8 KiB
Python
59 lines
1.8 KiB
Python
from typing import Iterator, Tuple, Union
|
|
|
|
from ...errors import Errors
|
|
from ...symbols import NOUN, PRON, PROPN
|
|
from ...tokens import Doc, Span
|
|
|
|
|
|
def noun_chunks(doclike: Union[Doc, Span]) -> Iterator[Tuple[int, int, int]]:
|
|
"""
|
|
Detect base noun phrases from a dependency parse. Works on both Doc and Span.
|
|
"""
|
|
# Please see documentation for Turkish NP structure
|
|
labels = [
|
|
"nsubj",
|
|
"iobj",
|
|
"obj",
|
|
"obl",
|
|
"appos",
|
|
"orphan",
|
|
"dislocated",
|
|
"ROOT",
|
|
]
|
|
doc = doclike.doc # Ensure works on both Doc and Span.
|
|
if not doc.has_annotation("DEP"):
|
|
raise ValueError(Errors.E029)
|
|
|
|
np_deps = [doc.vocab.strings.add(label) for label in labels]
|
|
conj = doc.vocab.strings.add("conj")
|
|
flat = doc.vocab.strings.add("flat")
|
|
np_label = doc.vocab.strings.add("NP")
|
|
|
|
def extend_right(w): # Playing a trick for flat
|
|
rindex = w.i + 1
|
|
for rdep in doc[w.i].rights: # Extend the span to right if there is a flat
|
|
if rdep.dep == flat and rdep.pos in (NOUN, PROPN):
|
|
rindex = rdep.i + 1
|
|
else:
|
|
break
|
|
return rindex
|
|
|
|
prev_end = len(doc) + 1
|
|
for i, word in reversed(list(enumerate(doclike))):
|
|
if word.pos not in (NOUN, PROPN, PRON):
|
|
continue
|
|
# Prevent nested chunks from being produced
|
|
if word.i >= prev_end:
|
|
continue
|
|
if word.dep in np_deps:
|
|
prev_end = word.left_edge.i
|
|
yield word.left_edge.i, extend_right(word), np_label
|
|
elif word.dep == conj:
|
|
cc_token = word.left_edge
|
|
prev_end = cc_token.i
|
|
# Shave off cc tokens from the NP
|
|
yield cc_token.right_edge.i + 1, extend_right(word), np_label
|
|
|
|
|
|
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}
|