spaCy/spacy/lang/en/syntax_iterators.py
Vishnu Priya VR 9ce059dd06
Limiting noun_chunks for specific languages (#5396)
* 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>
2020-05-14 12:58:06 +02:00

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",
"dobj",
"nsubjpass",
"pcomp",
"pobj",
"dative",
"appos",
"attr",
"ROOT",
]
doc = obj.doc # Ensure works on both Doc and Span.
if not doc.is_parsed:
raise ValueError(Errors.E029)
np_deps = [doc.vocab.strings.add(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.i + 1))
yield word.left_edge.i, word.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.i + 1))
yield word.left_edge.i, word.i + 1, np_label
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}