Defending Pre-trained Language Models from Adversarial Word Substitution Without Performance Sacrifice

Defending Pre-trained Language Models from Adversarial Word Substitution Without Performance Sacrifice Rongzhou Bao author Jiayi Wang author Hai Zhao author 2021-08 text Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 Chengqing Zong editor Fei Xia editor Wenjie Li editor Roberto Navigli editor Association for Computational Linguistics Online conference publication bao-etal-2021-defending 10.18653/v1/2021.findings-acl.287 https://aclanthology.org/2021.findings-acl.287/ 2021-08 3248 3258