BADGE: Speeding Up BERT Inference after Deployment via Block-wise Bypasses and Divergence-based Early Exiting Wei Zhu author Peng Wang author Yuan Ni author Guotong Xie author Xiaoling Wang author 2023-07 text Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track) Sunayana Sitaram editor Beata Beigman Klebanov editor Jason D Williams editor Association for Computational Linguistics Toronto, Canada conference publication zhu-etal-2023-badge 10.18653/v1/2023.acl-industry.48 https://aclanthology.org/2023.acl-industry.48/ 2023-07 500 509