Towards Trustworthy Explanation: On Causal Rationalization

Autor:	Zhang, Wenbo, Wu, Tong, Wang, Yunlong, Cai, Yong, Cai, Hengrui
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Computation and Language Statistics - Methodology Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	With recent advances in natural language processing, rationalization becomes an essential self-explaining diagram to disentangle the black box by selecting a subset of input texts to account for the major variation in prediction. Yet, existing association-based approaches on rationalization cannot identify true rationales when two or more snippets are highly inter-correlated and thus provide a similar contribution to prediction accuracy, so-called spuriousness. To address this limitation, we novelly leverage two causal desiderata, non-spuriousness and efficiency, into rationalization from the causal inference perspective. We formally define a series of probabilities of causation based on a newly proposed structural causal model of rationalization, with its theoretical identification established as the main component of learning necessary and sufficient rationales. The superior performance of the proposed causal rationalization is demonstrated on real-world review and medical datasets with extensive experiments compared to state-of-the-art methods. Comment: In Proceedings of the 40th International Conference on Machine Learning (ICML) GitHub Repository: https://github.com/onepounchman/Causal-Retionalization
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2306.14115 Zobrazit plný text záznamu View this record from Arxiv