@inproceedings{zhou-etal-2020-scheduled,
    title = "Scheduled {D}rop{H}ead: A Regularization Method for Transformer Models",
    author = "Zhou, Wangchunshu  and
      Ge, Tao  and
      Wei, Furu  and
      Zhou, Ming  and
      Xu, Ke",
    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/Author-page-Marten-During-lu/2020.findings-emnlp.178/",
    doi = "10.18653/v1/2020.findings-emnlp.178",
    pages = "1971--1980"
}