Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference

Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference Bang An author Jie Lyu author Zhenyi Wang author Chunyuan Li author Changwei Hu author Fei Tan author Ruiyi Zhang author Yifan Hu author Changyou Chen 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 an-etal-2020-repulsive 10.18653/v1/2020.emnlp-main.17 https://aclanthology.org/2020.emnlp-main.17/ 2020-11 236 255