Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers - ACL Anthology

Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers

Jieyu Zhao, Xuezhi Wang, Yao Qin, Jilin Chen, Kai-Wei Chang


Abstract
Large pre-trained language models have shown remarkable performance over the past few years. These models, however, sometimes learn superficial features from the dataset and cannot generalize to the distributions that are dissimilar to the training scenario. There have been several approaches proposed to reduce model’s reliance on these bias features which can improve model robustness in the out-of-distribution setting. However, existing methods usually use a fixed low-capacity model to deal with various bias features, which ignore the learnability of those features. In this paper, we analyze a set of existing bias features and demonstrate there is no single model that works best for all the cases. We further show that by choosing an appropriate bias model, we can obtain a better robustness result than baselines with a more sophisticated model design.
Anthology ID:
2022.findings-emnlp.118
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1634–1640
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.118
DOI:
10.18653/v1/2022.findings-emnlp.118
Bibkey:
Cite (ACL):
Jieyu Zhao, Xuezhi Wang, Yao Qin, Jilin Chen, and Kai-Wei Chang. 2022. Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 1634–1640, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers (Zhao et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.118.pdf