@inproceedings{zhu-etal-2023-badge,
    title = "{BADGE}: Speeding Up {BERT} Inference after Deployment via Block-wise Bypasses and Divergence-based Early Exiting",
    author = "Zhu, Wei  and
      Wang, Peng  and
      Ni, Yuan  and
      Xie, Guotong  and
      Wang, Xiaoling",
    editor = "Sitaram, Sunayana  and
      Beigman Klebanov, Beata  and
      Williams, Jason D",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.acl-industry.48/",
    doi = "10.18653/v1/2023.acl-industry.48",
    pages = "500--509"
}