@inproceedings{zhang-etal-2022-moefication,
    title = "{M}o{E}fication: Transformer Feed-forward Layers are Mixtures of Experts",
    author = "Zhang, Zhengyan  and
      Lin, Yankai  and
      Liu, Zhiyuan  and
      Li, Peng  and
      Sun, Maosong  and
      Zhou, Jie",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2022.findings-acl.71/",
    doi = "10.18653/v1/2022.findings-acl.71",
    pages = "877--890"
}