Pengwei Zhan, Yang Wu, Shaolei Zhou, Yunjian Zhang, Liming Wang. Mitigating the Inconsistency Between Word Saliency and Model Confidence with Pathological Contrastive Training. In Smaranda Muresan, Preslav Nakov, Aline Villavicencio, editors, Findings of the Association for Computational Linguistics: ACL 2022, Dublin, Ireland, May 22-27, 2022. pages 2226-2244, Association for Computational Linguistics, 2022. [doi]
Abstract is missing.