Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists

Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists Giuseppe Attanasio author Debora Nozza author Dirk Hovy author Elena Baralis author 2022-05 text Findings of the Association for Computational Linguistics: ACL 2022 Smaranda Muresan editor Preslav Nakov editor Aline Villavicencio editor Association for Computational Linguistics Dublin, Ireland conference publication attanasio-etal-2022-entropy 10.18653/v1/2022.findings-acl.88 https://aclanthology.org/2022.findings-acl.88/ 2022-05 1105 1119