Tsai, Yao-Hung Hubert, Bai, Shaojie, Yamada, Makoto, Morency, Louis-Philippe, and Salakhutdinov, Ruslan. Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel. Retrieved from https://par.nsf.gov/biblio/10125397. Proceedings of the Conference on Empirical Methods in Natural Language Processing . Web. doi:10.18653/v1/D19-1443.

Tsai, Yao-Hung Hubert, Bai, Shaojie, Yamada, Makoto, Morency, Louis-Philippe, & Salakhutdinov, Ruslan. Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel. Proceedings of the Conference on Empirical Methods in Natural Language Processing, (). Retrieved from https://par.nsf.gov/biblio/10125397. https://doi.org/10.18653/v1/D19-1443

Tsai, Yao-Hung Hubert, Bai, Shaojie, Yamada, Makoto, Morency, Louis-Philippe, and Salakhutdinov, Ruslan. "Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel". Proceedings of the Conference on Empirical Methods in Natural Language Processing (). Country unknown/Code not available. https://doi.org/10.18653/v1/D19-1443. https://par.nsf.gov/biblio/10125397.

@article{osti_10125397,
place = {Country unknown/Code not available}, title = {Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel}, url = {https://par.nsf.gov/biblio/10125397}, DOI = {10.18653/v1/D19-1443}, abstractNote = {}, journal = {Proceedings of the Conference on Empirical Methods in Natural Language Processing}, author = {Tsai, Yao-Hung Hubert and Bai, Shaojie and Yamada, Makoto and Morency, Louis-Philippe and Salakhutdinov, Ruslan}, }