mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 09:56:28 +03:00
e3222fdec9
* add syntax iterators for danish * add test noun chunks for danish syntax iterators * add contributor agreement * update da syntax iterators to remove nested chunks * add tests for da noun chunks * Fix test * add missing import * fix example * Prevent overlapping noun chunks Prevent overlapping noun chunks by tracking the end index of the previous noun chunk span. Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
82 lines
2.2 KiB
Python
82 lines
2.2 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...symbols import NOUN, PROPN, PRON, VERB, AUX
|
|
from ...errors import Errors
|
|
|
|
|
|
def noun_chunks(doclike):
|
|
def is_verb_token(tok):
|
|
return tok.pos in [VERB, AUX]
|
|
|
|
def next_token(tok):
|
|
try:
|
|
return tok.nbor()
|
|
except IndexError:
|
|
return None
|
|
|
|
def get_left_bound(doc, root):
|
|
left_bound = root
|
|
for tok in reversed(list(root.lefts)):
|
|
if tok.dep in np_left_deps:
|
|
left_bound = tok
|
|
return left_bound
|
|
|
|
def get_right_bound(doc, root):
|
|
right_bound = root
|
|
for tok in root.rights:
|
|
if tok.dep in np_right_deps:
|
|
right = get_right_bound(doc, tok)
|
|
if list(
|
|
filter(
|
|
lambda t: is_verb_token(t) or t.dep in stop_deps,
|
|
doc[root.i : right.i],
|
|
)
|
|
):
|
|
break
|
|
else:
|
|
right_bound = right
|
|
return right_bound
|
|
|
|
def get_bounds(doc, root):
|
|
return get_left_bound(doc, root), get_right_bound(doc, root)
|
|
|
|
doc = doclike.doc
|
|
|
|
if not doc.is_parsed:
|
|
raise ValueError(Errors.E029)
|
|
|
|
if not len(doc):
|
|
return
|
|
|
|
left_labels = [
|
|
"det",
|
|
"fixed",
|
|
"nmod:poss",
|
|
"amod",
|
|
"flat",
|
|
"goeswith",
|
|
"nummod",
|
|
"appos",
|
|
]
|
|
right_labels = ["fixed", "nmod:poss", "amod", "flat", "goeswith", "nummod", "appos"]
|
|
stop_labels = ["punct"]
|
|
|
|
np_label = doc.vocab.strings.add("NP")
|
|
np_left_deps = [doc.vocab.strings.add(label) for label in left_labels]
|
|
np_right_deps = [doc.vocab.strings.add(label) for label in right_labels]
|
|
stop_deps = [doc.vocab.strings.add(label) for label in stop_labels]
|
|
|
|
chunks = []
|
|
prev_right = -1
|
|
for token in doclike:
|
|
if token.pos in [PROPN, NOUN, PRON]:
|
|
left, right = get_bounds(doc, token)
|
|
if left.i <= prev_right:
|
|
continue
|
|
yield left.i, right.i + 1, np_label
|
|
prev_right = right.i
|
|
|
|
|
|
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}
|