Double Trouble: How to not Explain a Text Classifier’s Decisions Using Counterfactuals Synthesized by Masked Language Models?

Double Trouble: How to not Explain a Text Classifier’s Decisions Using Counterfactuals Synthesized by Masked Language Models? Thang Pham author Trung Bui author Long Mai author Anh Nguyen author 2022-11 text Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) Yulan He editor Heng Ji editor Sujian Li editor Yang Liu editor Chua-Hui Chang editor Association for Computational Linguistics Online only conference publication pham-etal-2022-double 10.18653/v1/2022.aacl-main.2 https://aclanthology.org/2022.aacl-main.2/ 2022-11 12 31