Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attacks

Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attacks Zhao Meng author Yihan Dong author Mrinmaya Sachan author Roger Wattenhofer author 2022-07 text Findings of the Association for Computational Linguistics: NAACL 2022 Marine Carpuat editor Marie-Catherine de Marneffe editor Ivan Vladimir Meza Ruiz editor Association for Computational Linguistics Seattle, United States conference publication meng-etal-2022-self 10.18653/v1/2022.findings-naacl.8 https://aclanthology.org/2022.findings-naacl.8/ 2022-07 87 101