spaCy/spacy/lang/es/syntax_iterators.py

59 lines
2.0 KiB
Python
Raw Normal View History

2021-01-15 03:57:36 +03:00
from typing import Union, Iterator
2017-06-02 20:09:58 +03:00
from ...symbols import NOUN, PROPN, PRON, VERB, AUX
from ...errors import Errors
from ...tokens import Doc, Span, Token
2017-06-02 20:09:58 +03:00
def noun_chunks(doclike: Union[Doc, Span]) -> Iterator[Span]:
"""Detect base noun phrases from a dependency parse. Works on Doc and Span."""
doc = doclike.doc
if not doc.has_annotation("DEP"):
raise ValueError(Errors.E029)
if not len(doc):
return
np_label = doc.vocab.strings.add("NP")
left_labels = ["det", "fixed", "neg"] # ['nunmod', 'det', 'appos', 'fixed']
right_labels = ["flat", "fixed", "compound", "neg"]
stop_labels = ["punct"]
np_left_deps = [doc.vocab.strings.add(label) for label in left_labels]
np_right_deps = [doc.vocab.strings.add(label) for label in right_labels]
stop_deps = [doc.vocab.strings.add(label) for label in stop_labels]
prev_right = -1
for token in doclike:
2017-06-02 20:09:58 +03:00
if token.pos in [PROPN, NOUN, PRON]:
left, right = noun_bounds(
doc, token, np_left_deps, np_right_deps, stop_deps
)
if left.i <= prev_right:
continue
yield left.i, right.i + 1, np_label
prev_right = right.i
2017-06-02 20:09:58 +03:00
def is_verb_token(token: Token) -> bool:
2017-06-02 20:09:58 +03:00
return token.pos in [VERB, AUX]
def noun_bounds(doc, root, np_left_deps, np_right_deps, stop_deps):
2017-06-02 20:09:58 +03:00
left_bound = root
for token in reversed(list(root.lefts)):
if token.dep in np_left_deps:
left_bound = token
right_bound = root
for token in root.rights:
if token.dep in np_right_deps:
left, right = noun_bounds(
doc, token, np_left_deps, np_right_deps, stop_deps
)
filter_func = lambda t: is_verb_token(t) or t.dep in stop_deps
2020-09-29 22:39:28 +03:00
if list(filter(filter_func, doc[left_bound.i : right.i])):
2017-06-02 20:09:58 +03:00
break
else:
right_bound = right
return left_bound, right_bound
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}