mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 09:56:28 +03:00
b98d216205
* Update Catalan language data Update Catalan language data based on contributions from the Text Mining Unit at the Barcelona Supercomputing Center: https://github.com/TeMU-BSC/spacy4release/tree/main/lang_data * Update tokenizer settings for UD Catalan AnCora Update for UD Catalan AnCora v2.7 with merged multi-word tokens. * Update test * Move prefix patternt to more generic infix pattern * Clean up
47 lines
1.8 KiB
Python
47 lines
1.8 KiB
Python
from ...symbols import NOUN, PROPN
|
|
from ...errors import Errors
|
|
|
|
|
|
def noun_chunks(doclike):
|
|
"""Detect base noun phrases from a dependency parse. Works on Doc and Span."""
|
|
# fmt: off
|
|
labels = ["nsubj", "nsubj:pass", "obj", "obl", "iobj", "ROOT", "appos", "nmod", "nmod:poss"]
|
|
# fmt: on
|
|
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[label] for label in labels]
|
|
np_label = doc.vocab.strings.add("NP")
|
|
prev_end = -1
|
|
for i, word in enumerate(doclike):
|
|
if word.pos not in (NOUN, PROPN):
|
|
continue
|
|
# Prevent nested chunks from being produced
|
|
if word.left_edge.i <= prev_end:
|
|
continue
|
|
if word.dep in np_deps:
|
|
left = word.left_edge.i
|
|
right = word.right_edge.i + 1
|
|
# leave prepositions and punctuation out of the left side of the chunk
|
|
if word.left_edge.pos_ == "ADP" or word.left_edge.pos_ == "PUNCT":
|
|
left = word.left_edge.i + 1
|
|
prev_end = word.right_edge.i
|
|
# leave subordinated clauses and appositions out of the chunk
|
|
a = word.i + 1
|
|
while a < word.right_edge.i:
|
|
paraula = doc[a]
|
|
if paraula.pos_ == "VERB":
|
|
right = paraula.left_edge.i
|
|
prev_end = paraula.left_edge.i - 1
|
|
elif paraula.dep_ == "appos":
|
|
right = paraula.left_edge.i + 1
|
|
prev_end = paraula.left_edge.i - 1
|
|
a += 1
|
|
# leave punctuation out of the right side of the chunk
|
|
if word.right_edge.pos_ == "PUNCT":
|
|
right = right - 1
|
|
yield left, right, np_label
|
|
|
|
|
|
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}
|