@article{si-etal-2023-sub,
    title = "Sub-Character Tokenization for {C}hinese Pretrained Language Models",
    author = "Si, Chenglei  and
      Zhang, Zhengyan  and
      Chen, Yingfa  and
      Qi, Fanchao  and
      Wang, Xiaozhi  and
      Liu, Zhiyuan  and
      Wang, Yasheng  and
      Liu, Qun  and
      Sun, Maosong",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "11",
    year = "2023",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.tacl-1.28/",
    doi = "10.1162/tacl_a_00560",
    pages = "469--487"
}