@inproceedings{tao-etal-2022-compression,
    title = "Compression of Generative Pre-trained Language Models via Quantization",
    author = "Tao, Chaofan  and
      Hou, Lu  and
      Zhang, Wei  and
      Shang, Lifeng  and
      Jiang, Xin  and
      Liu, Qun  and
      Luo, Ping  and
      Wong, Ngai",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.acl-long.331/",
    doi = "10.18653/v1/2022.acl-long.331",
    pages = "4821--4836"
}