@inproceedings{li-etal-2019-information,
    title = "Information Aggregation for Multi-Head Attention with Routing-by-Agreement",
    author = "Li, Jian  and
      Yang, Baosong  and
      Dou, Zi-Yi  and
      Wang, Xing  and
      Lyu, Michael R.  and
      Tu, Zhaopeng",
    editor = "Burstein, Jill  and
      Doran, Christy  and
      Solorio, Thamar",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/N19-1359/",
    doi = "10.18653/v1/N19-1359",
    pages = "3566--3575"
}