@inproceedings{fan-etal-2021-mask,
    title = "Mask Attention Networks: Rethinking and Strengthen Transformer",
    author = "Fan, Zhihao  and
      Gong, Yeyun  and
      Liu, Dayiheng  and
      Wei, Zhongyu  and
      Wang, Siyuan  and
      Jiao, Jian  and
      Duan, Nan  and
      Zhang, Ruofei  and
      Huang, Xuanjing",
    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://preview.aclanthology.org/fix-sig-urls/2021.naacl-main.135/",
    doi = "10.18653/v1/2021.naacl-main.135",
    pages = "1692--1701"
}