Commit Graph

3 Commits (a5c1e0946906235c20149ae643fedd8f7f281c66)

Author SHA1 Message Date
qianlong cae77c0c22 BasicTokenizer not case fold on preserverd words
5 years ago
qianlong 980ddd32a2 change output of WordpieceTokenizer and BertTokenizer to 1-D string tensors
5 years ago
qianlong 4f16f036be Add WhitespaceTokenizer and UnicodeScriptTokenizer for nlp
5 years ago