spaCy/spacy/zh/__init__.py

14 lines
283 B
Python
Raw Normal View History

from ..language import Language
2016-04-24 20:11:38 +03:00
from .jieba import JiebaTokenizer
class Chinese(Language):
lang = u'zh'
2016-04-24 20:11:38 +03:00
@classmethod
def default_tokenizer(cls, package, vocab):
'''Return Jieba-wrapper tokenizer.'''
return JiebaTokenizer.from_package(package, vocab)