Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads? Zae Myung Kim author Laurent Besacier author Vassilina Nikoulina author Didier Schwab author 2021-08 text Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 Chengqing Zong editor Fei Xia editor Wenjie Li editor Roberto Navigli editor Association for Computational Linguistics Online conference publication kim-etal-2021-multilingual 10.18653/v1/2021.findings-acl.250 https://aclanthology.org/2021.findings-acl.250/ 2021-08 2832 2841