Reducing Spurious Correlations for Answer Selection by Feature Decorrelation and Language Debiasing

Zeyi Zhong, Min Yang, Ruifeng Xu


Abstract
Deep neural models have become the mainstream in answer selection, yielding state-of-the-art performance. However, these models tend to rely on spurious correlations between prediction labels and input features, which in general suffer from robustness and generalization. In this paper, we propose a novel Spurious Correlation reduction method to improve the robustness of the neural ANswer selection models (SCAN) from the sample and feature perspectives by removing the feature dependencies and language biases in answer selection. First, from the sample perspective, we propose a feature decorrelation module by learning a weight for each instance at the training phase to remove the feature dependencies and reduce the spurious correlations without prior knowledge of such correlations. Second, from the feature perspective, we propose a feature debiasing module with contrastive learning to alleviate the negative language biases (spurious correlations) and further improve the robustness of the AS models. Experimental results on three benchmark datasets show that SCAN achieves substantial improvements over strong baselines. For reproducibility, we will release our code and data upon the publication of this paper.
Anthology ID:
2022.coling-1.151
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony Kyungil Lee, Enrico Santus, Francis Bond, Seung-Hoon Na
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1753–1764
Language:
URL:
https://aclanthology.org/2022.coling-1.151
DOI:
Bibkey:
Cite (ACL):
Zeyi Zhong, Min Yang, and Ruifeng Xu. 2022. Reducing Spurious Correlations for Answer Selection by Feature Decorrelation and Language Debiasing. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1753–1764, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Reducing Spurious Correlations for Answer Selection by Feature Decorrelation and Language Debiasing (Zhong et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.151.pdf
Code
 xish9/scan
Data
SelQAWikiQA