Interventional Rationalization

Linan Yue, Qi Liu, Li Wang, Yanqing An, Yichao Du, Zhenya Huang


Abstract
Selective rationalizations improve the explainability of neural networks by selecting a subsequence of the input (i.e., rationales) to explain the prediction results. Although existing methods have achieved promising results, they still suffer from adopting the spurious correlations in data (aka., shortcuts) to compose rationales and make predictions. Inspired by the causal theory, in this paper, we develop an interventional rationalization (Inter-RAT) to discover the causal rationales. Specifically, we first analyse the causalities among the input, rationales and results with a structural causal model. Then, we discover spurious correlations between the input and rationales, and between rationales and results, respectively, by identifying the confounder in the causalities. Next, based on the backdoor adjustment, we propose a causal intervention method to remove the spurious correlations between input and rationales. Further, we discuss reasons why spurious correlations between the selected rationales and results exist by analysing the limitations of the sparsity constraint in the rationalization, and employ the causal intervention method to remove these correlations. Extensive experimental results on three real-world datasets clearly validate the effectiveness of our proposed method. The source code of Inter-RAT is available at https://github.com/yuelinan/Codes-of-Inter-RAT.
Anthology ID:
2023.emnlp-main.700
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11404–11418
Language:
URL:
https://aclanthology.org/2023.emnlp-main.700
DOI:
10.18653/v1/2023.emnlp-main.700
Bibkey:
Cite (ACL):
Linan Yue, Qi Liu, Li Wang, Yanqing An, Yichao Du, and Zhenya Huang. 2023. Interventional Rationalization. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11404–11418, Singapore. Association for Computational Linguistics.
Cite (Informal):
Interventional Rationalization (Yue et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.700.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.700.mp4