spaCy/spacy/lang/el/syntax_iterators.py
Daniël de Kok e2b70df012
Configure isort to use the Black profile, recursively isort the spacy module (#12721)
* 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
2023-06-14 17:48:41 +02:00

54 lines
2.2 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 Doc and Span."""
# It follows the logic of the noun chunks finder of English language,
# adjusted to some Greek language special characteristics.
# obj tag corrects some DEP tagger mistakes.
# Further improvement of the models will eliminate the need for this tag.
labels = ["nsubj", "obj", "iobj", "appos", "ROOT", "obl"]
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")
nmod = doc.vocab.strings.add("nmod")
np_label = doc.vocab.strings.add("NP")
prev_end = -1
for i, word in enumerate(doclike):
if word.pos not in (NOUN, PROPN, PRON):
continue
# Prevent nested chunks from being produced
if word.left_edge.i <= prev_end:
continue
if word.dep in np_deps:
flag = False
if word.pos == NOUN:
# check for patterns such as γραμμή παραγωγής
for potential_nmod in word.rights:
if potential_nmod.dep == nmod:
prev_end = potential_nmod.i
yield word.left_edge.i, potential_nmod.i + 1, np_label
flag = True
break
if flag is False:
prev_end = word.i
yield word.left_edge.i, word.i + 1, np_label
elif word.dep == conj:
# covers the case: έχει όμορφα και έξυπνα παιδιά
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.i
yield word.left_edge.i, word.i + 1, np_label
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}