BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover’s Distance

BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover’s Distance Jianquan Li author Xiaokang Liu author Honghong Zhao author Ruifeng Xu author Min Yang author Yaohong Jin author 2020-11 text Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) Bonnie Webber editor Trevor Cohn editor Yulan He editor Yang Liu editor Association for Computational Linguistics Online conference publication li-etal-2020-bert 10.18653/v1/2020.emnlp-main.242 https://aclanthology.org/2020.emnlp-main.242/ 2020-11 3009 3018