@inproceedings{zhang-etal-2022-mixture,
    title = "Mixture of Attention Heads: Selecting Attention Heads Per Token",
    author = "Zhang, Xiaofeng  and
      Shen, Yikang  and
      Huang, Zeyu  and
      Zhou, Jie  and
      Rong, Wenge  and
      Xiong, Zhang",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.emnlp-main.278/",
    doi = "10.18653/v1/2022.emnlp-main.278",
    pages = "4150--4162"
}