Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models Shun Kiyono author Sho Takase author Jun Suzuki author Naoaki Okazaki author Kentaro Inui author Masaaki Nagata author 2018-11 text Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP Tal Linzen editor Grzegorz Chrupała editor Afra Alishahi editor Association for Computational Linguistics Brussels, Belgium conference publication kiyono-etal-2018-unsupervised 10.18653/v1/W18-5410 https://aclanthology.org/W18-5410/ 2018-11 74 81