Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search

Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search Gyuwan Kim author Kyunghyun Cho 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 kim-cho-2021-length 10.18653/v1/2021.acl-long.508 https://aclanthology.org/2021.acl-long.508/ 2021-08 6501 6511