Multi-Head Attention with Disagreement Regularization Jian Li author Zhaopeng Tu author Baosong Yang author Michael R Lyu author Tong Zhang author 2018-oct-nov text Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing Ellen Riloff editor David Chiang editor Julia Hockenmaier editor Jun’ichi Tsujii editor Association for Computational Linguistics Brussels, Belgium conference publication li-etal-2018-multi-head 10.18653/v1/D18-1317 https://aclanthology.org/D18-1317/ 2018-oct-nov 2897 2903