@inproceedings{kudugunta-etal-2021-beyond-distillation,
    title = "Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference",
    author = "Kudugunta, Sneha  and
      Huang, Yanping  and
      Bapna, Ankur  and
      Krikun, Maxim  and
      Lepikhin, Dmitry  and
      Luong, Minh-Thang  and
      Firat, Orhan",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.findings-emnlp.304/",
    doi = "10.18653/v1/2021.findings-emnlp.304",
    pages = "3577--3599"
}