Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models

Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models Tyler A Chang author Yifan Xu author Weijian Xu author Zhuowen Tu 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 chang-etal-2021-convolutions 10.18653/v1/2021.acl-long.333 https://aclanthology.org/2021.acl-long.333/ 2021-08 4322 4333