Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective
This addresses dataset bias in NLU models, improving robustness for applications like text classification, but it is incremental as it builds on existing debiasing methods.
The paper tackles the problem of spurious correlations in natural language understanding models, which cause poor out-of-distribution performance, by proposing a method to decorrelate and purify features, resulting in superior performance compared to other approaches on two NLU tasks.
Natural language understanding (NLU) models tend to rely on spurious correlations (i.e., dataset bias) to achieve high performance on in-distribution datasets but poor performance on out-of-distribution ones. Most of the existing debiasing methods often identify and weaken these samples with biased features (i.e., superficial surface features that cause such spurious correlations). However, down-weighting these samples obstructs the model in learning from the non-biased parts of these samples. To tackle this challenge, in this paper, we propose to eliminate spurious correlations in a fine-grained manner from a feature space perspective. Specifically, we introduce Random Fourier Features and weighted re-sampling to decorrelate the dependencies between features to mitigate spurious correlations. After obtaining decorrelated features, we further design a mutual-information-based method to purify them, which forces the model to learn features that are more relevant to tasks. Extensive experiments on two well-studied NLU tasks demonstrate that our method is superior to other comparative approaches.