Fix Spanish noun_chunks (resolves #2210)

Make sure 'NP' label is added to StringStore and move noun_bounds helper into a closure to allow reusing label sets
This commit is contained in:
ines 2018-04-18 18:44:01 -04:00
parent 9632595fb4
commit 686225eadd
1 changed files with 19 additions and 19 deletions

View File

@ -6,13 +6,30 @@ from ...symbols import NOUN, PROPN, PRON, VERB, AUX
def noun_chunks(obj):
doc = obj.doc
np_label = doc.vocab.strings['NP']
left_labels = ['det', 'fixed', 'neg'] #['nunmod', 'det', 'appos', 'fixed']
np_label = doc.vocab.strings.add('NP')
left_labels = ['det', 'fixed', 'neg'] # ['nunmod', 'det', 'appos', 'fixed']
right_labels = ['flat', 'fixed', 'compound', 'neg']
stop_labels = ['punct']
np_left_deps = [doc.vocab.strings[label] for label in left_labels]
np_right_deps = [doc.vocab.strings[label] for label in right_labels]
stop_deps = [doc.vocab.strings[label] for label in stop_labels]
def noun_bounds(root):
left_bound = root
for token in reversed(list(root.lefts)):
if token.dep in np_left_deps:
left_bound = token
right_bound = root
for token in root.rights:
if (token.dep in np_right_deps):
left, right = noun_bounds(token)
if list(filter(lambda t: is_verb_token(t) or t.dep in stop_deps,
doc[left_bound.i: right.i])):
break
else:
right_bound = right
return left_bound, right_bound
token = doc[0]
while token and token.i < len(doc):
if token.pos in [PROPN, NOUN, PRON]:
@ -33,23 +50,6 @@ def next_token(token):
return None
def noun_bounds(root):
left_bound = root
for token in reversed(list(root.lefts)):
if token.dep in np_left_deps:
left_bound = token
right_bound = root
for token in root.rights:
if (token.dep in np_right_deps):
left, right = noun_bounds(token)
if list(filter(lambda t: is_verb_token(t) or t.dep in stop_deps,
doc[left_bound.i: right.i])):
break
else:
right_bound = right
return left_bound, right_bound
SYNTAX_ITERATORS = {
'noun_chunks': noun_chunks
}