Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation Yuanxin Liu author Fandong Meng author Zheng Lin author Weiping Wang author Jie Zhou author 2021-08 text Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) Chengqing Zong editor Fei Xia editor Wenjie Li editor Roberto Navigli editor Association for Computational Linguistics Online conference publication liu-etal-2021-marginal 10.18653/v1/2021.acl-long.228 https://aclanthology.org/2021.acl-long.228/ 2021-08 2928 2941