@inproceedings{xu-etal-2023-towards-parameter,
    title = "Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity",
    author = "Xu, Haoran  and
      Elbayad, Maha  and
      Murray, Kenton  and
      Maillard, Jean  and
      Goswami, Vedanuj",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/2023.findings-emnlp.856/",
    doi = "10.18653/v1/2023.findings-emnlp.856",
    pages = "12858--12870"
}