@inproceedings{gu-etal-2021-transformer,
    title = "On the Transformer Growth for Progressive {BERT} Training",
    author = "Gu, Xiaotao  and
      Liu, Liyuan  and
      Yu, Hongkun  and
      Li, Jing  and
      Chen, Chen  and
      Han, Jiawei",
    editor = "Toutanova, Kristina  and
      Rumshisky, Anna  and
      Zettlemoyer, Luke  and
      Hakkani-Tur, Dilek  and
      Beltagy, Iz  and
      Bethard, Steven  and
      Cotterell, Ryan  and
      Chakraborty, Tanmoy  and
      Zhou, Yichao",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.naacl-main.406/",
    doi = "10.18653/v1/2021.naacl-main.406",
    pages = "5174--5180"
}