mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 13:47:13 +03:00
9b4979407d
Add a similar fix as in #5470 to prevent the German noun chunks iterator from producing overlapping spans.
60 lines
1.8 KiB
Python
60 lines
1.8 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...symbols import NOUN, PROPN, PRON
|
|
from ...errors import Errors
|
|
|
|
|
|
def noun_chunks(doclike):
|
|
"""
|
|
Detect base noun phrases from a dependency parse. Works on both Doc and Span.
|
|
"""
|
|
# this iterator extracts spans headed by NOUNs starting from the left-most
|
|
# syntactic dependent until the NOUN itself for close apposition and
|
|
# measurement construction, the span is sometimes extended to the right of
|
|
# the NOUN. Example: "eine Tasse Tee" (a cup (of) tea) returns "eine Tasse Tee"
|
|
# and not just "eine Tasse", same for "das Thema Familie".
|
|
labels = [
|
|
"sb",
|
|
"oa",
|
|
"da",
|
|
"nk",
|
|
"mo",
|
|
"ag",
|
|
"ROOT",
|
|
"root",
|
|
"cj",
|
|
"pd",
|
|
"og",
|
|
"app",
|
|
]
|
|
doc = doclike.doc # Ensure works on both Doc and Span.
|
|
|
|
if not doc.is_parsed:
|
|
raise ValueError(Errors.E029)
|
|
|
|
np_label = doc.vocab.strings.add("NP")
|
|
np_deps = set(doc.vocab.strings.add(label) for label in labels)
|
|
close_app = doc.vocab.strings.add("nk")
|
|
|
|
rbracket = 0
|
|
prev_end = -1
|
|
for i, word in enumerate(doclike):
|
|
if i < rbracket:
|
|
continue
|
|
# Prevent nested chunks from being produced
|
|
if word.left_edge.i <= prev_end:
|
|
continue
|
|
if word.pos in (NOUN, PROPN, PRON) and word.dep in np_deps:
|
|
rbracket = word.i + 1
|
|
# try to extend the span to the right
|
|
# to capture close apposition/measurement constructions
|
|
for rdep in doc[word.i].rights:
|
|
if rdep.pos in (NOUN, PROPN) and rdep.dep == close_app:
|
|
rbracket = rdep.i + 1
|
|
prev_end = rbracket - 1
|
|
yield word.left_edge.i, rbracket, np_label
|
|
|
|
|
|
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}
|