Improving the Adversarial Robustness of NLP Models by Information Bottleneck

Improving the Adversarial Robustness of NLP Models by Information Bottleneck Cenyuan Zhang author Xiang Zhou author Yixin Wan author Xiaoqing Zheng author Kai-Wei Chang author Cho-Jui Hsieh 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 zhang-etal-2022-improving 10.18653/v1/2022.findings-acl.284 https://aclanthology.org/2022.findings-acl.284/ 2022-05 3588 3598