Analyzing the Structure of Attention in a Transformer Language Model Jesse Vig author Yonatan Belinkov author 2019-08 text Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP Tal Linzen editor Grzegorz Chrupała editor Yonatan Belinkov editor Dieuwke Hupkes editor Association for Computational Linguistics Florence, Italy conference publication vig-belinkov-2019-analyzing 10.18653/v1/W19-4808 https://aclanthology.org/W19-4808/ 2019-08 63 76