SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing Taku Kudo author John Richardson author 2018-11 text Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations Eduardo Blanco editor Wei Lu editor Association for Computational Linguistics Brussels, Belgium conference publication kudo-richardson-2018-sentencepiece 10.18653/v1/D18-2012 https://aclanthology.org/D18-2012/ 2018-11 66 71