Analyzing the Structure of Attention in a Transformer Language Model

Jesse Vig, Yonatan Belinkov. Analyzing the Structure of Attention in a Transformer Language Model. In Tal Linzen, Grzegorz Chrupala, Yonatan Belinkov, Dieuwke Hupkes, editors, Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP@ACL 2019, Florence, Italy, August 1, 2019. pages 63-76, Association for Computational Linguistics, 2019. [doi]

Abstract

Abstract is missing.