Debiasing NLU models via causal intervention and counterfactual reasoning

• Main Authors: TIAN, Bing, CAO, Yixin, ZHANG, Yong, XING, Chunxiao
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/7454; https://ink.library.smu.edu.sg/context/sis_research/article/8457/viewcontent/21389_Article_Text_25402_1_2_20220628.pdf
• Institution: Singapore Management University

Recent studies have shown that strong Natural Language Understanding (NLU) models are prone to relying on annotation biases of the datasets as a shortcut, which goes against the underlying mechanisms of the task of interest. To reduce such biases, several recent works introduce debiasing methods to...