%0 Conference Proceedings
%T Transformer Dissection: An Unified Understanding for Transformer‘s Attention via the Lens of Kernel
%A Tsai, Yao-Hung Hubert
%A Bai, Shaojie
%A Yamada, Makoto
%A Morency, Louis-Philippe
%A Salakhutdinov, Ruslan
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F tsai-etal-2019-transformer
%R 10.18653/v1/D19-1443
%U https://aclanthology.org/D19-1443/
%U https://doi.org/10.18653/v1/D19-1443
%P 4344-4353