@inproceedings{liu-etal-2020-understanding,
    title = "Understanding the Difficulty of Training Transformers",
    author = "Liu, Liyuan  and
      Liu, Xiaodong  and
      Gao, Jianfeng  and
      Chen, Weizhu  and
      Han, Jiawei",
    editor = "Webber, Bonnie  and
      Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.emnlp-main.463/",
    doi = "10.18653/v1/2020.emnlp-main.463",
    pages = "5747--5763"
}