mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 05:37:03 +03:00
9ce059dd06
* Limiting noun_chunks for specific langauges * Limiting noun_chunks for specific languages Contributor Agreement * Addressing review comments * Removed unused fixtures and imports * Add fa_tokenizer in test suite * Use fa_tokenizer in test * Undo extraneous reformatting Co-authored-by: adrianeboyd <adrianeboyd@gmail.com>
56 lines
1.7 KiB
Python
56 lines
1.7 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...symbols import NOUN, PROPN, PRON
|
|
from ...errors import Errors
|
|
|
|
|
|
def noun_chunks(obj):
|
|
"""
|
|
Detect base noun phrases from a dependency parse. Works on both Doc and Span.
|
|
"""
|
|
labels = [
|
|
"nsubj",
|
|
"nsubj:pass",
|
|
"dobj",
|
|
"obj",
|
|
"iobj",
|
|
"ROOT",
|
|
"appos",
|
|
"nmod",
|
|
"nmod:poss",
|
|
]
|
|
doc = obj.doc # Ensure works on both Doc and Span.
|
|
|
|
if not doc.is_parsed:
|
|
raise ValueError(Errors.E029)
|
|
|
|
np_deps = [doc.vocab.strings[label] for label in labels]
|
|
conj = doc.vocab.strings.add("conj")
|
|
np_label = doc.vocab.strings.add("NP")
|
|
seen = set()
|
|
for i, word in enumerate(obj):
|
|
if word.pos not in (NOUN, PROPN, PRON):
|
|
continue
|
|
# Prevent nested chunks from being produced
|
|
if word.i in seen:
|
|
continue
|
|
if word.dep in np_deps:
|
|
if any(w.i in seen for w in word.subtree):
|
|
continue
|
|
seen.update(j for j in range(word.left_edge.i, word.right_edge.i + 1))
|
|
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
|
elif word.dep == conj:
|
|
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:
|
|
if any(w.i in seen for w in word.subtree):
|
|
continue
|
|
seen.update(j for j in range(word.left_edge.i, word.right_edge.i + 1))
|
|
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
|
|
|
|
|
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}
|