Fix german noun chunks iterator

This commit is contained in:
Matthew Honnibal 2017-05-28 20:13:03 +02:00
parent fd9b6722a9
commit 9239f06ed3

View File

@ -48,9 +48,9 @@ def english_noun_chunks(obj):
def german_noun_chunks(obj): def german_noun_chunks(obj):
labels = ['sb', 'oa', 'da', 'nk', 'mo', 'ag', 'ROOT', 'root', 'cj', 'pd', 'og', 'app'] labels = ['sb', 'oa', 'da', 'nk', 'mo', 'ag', 'ROOT', 'root', 'cj', 'pd', 'og', 'app']
doc = obj.doc # Ensure works on both Doc and Span. doc = obj.doc # Ensure works on both Doc and Span.
np_label = doc.vocab.strings['NP'] np_label = doc.vocab.strings.add('NP')
np_deps = set(doc.vocab.strings[label] for label in labels) np_deps = set(doc.vocab.strings.add(label) for label in labels)
close_app = doc.vocab.strings['nk'] close_app = doc.vocab.strings.add('nk')
rbracket = 0 rbracket = 0
for i, word in enumerate(obj): for i, word in enumerate(obj):