@inproceedings{bostrom-durrett-2020-byte,
    title = "Byte Pair Encoding is Suboptimal for Language Model Pretraining",
    author = "Bostrom, Kaj  and
      Durrett, Greg",
    editor = "Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.findings-emnlp.414/",
    doi = "10.18653/v1/2020.findings-emnlp.414",
    pages = "4617--4624"
}