Dynamically Disentangling Social Bias from Task-Oriented Representations with Adversarial Attack
Liwen Wang, Yuanmeng Yan, Keqing He, Yanan Wu, Weiran Xu
Abstract
Liwen Wang, Yuanmeng Yan, Keqing He, Yanan Wu, Weiran Xu. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.
Topics & Concepts
Adversarial systemComputer scienceTask (project management)Computational linguisticsAssociation (psychology)Natural language processingCognitive scienceArtificial intelligenceLinguisticsPsychologyEpistemologyEngineeringPhilosophySystems engineeringAdversarial Robustness in Machine LearningHate Speech and Cyberbullying DetectionEthics and Social Impacts of AI