Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers
This addresses robustness issues in text classification for AI applications, but it is incremental as it builds on existing ensemble methods.
The paper tackled the problem of text classifiers relying on superficial features that reduce robustness in out-of-distribution settings, showing that selecting appropriate bias models improves robustness over baselines with more sophisticated designs.
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.