Byte Pair Encoding is Suboptimal for Language Model Pretraining Kaj Bostrom author Greg Durrett author 2020-11 text Findings of the Association for Computational Linguistics: EMNLP 2020 Trevor Cohn editor Yulan He editor Yang Liu editor Association for Computational Linguistics Online conference publication bostrom-durrett-2020-byte 10.18653/v1/2020.findings-emnlp.414 https://aclanthology.org/2020.findings-emnlp.414/ 2020-11 4617 4624