Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis
Preprint
Abstract
Recent research has revealed that deep learning models have a tendency to leverage spurious correlations that exist in the training set but may not hold true in general circumstances. For instance, a sentiment classifier may erroneously learn that the token performances is commonly associated with positive movie reviews. Relying on these spurious correlations degrades the classifiers performance when it deploys on out-of-distribution data. In this paper, we examine the implications of spurious correlations through a novel perspective called neighborhood analysis. The analysis uncovers how spurious correlations lead unrelated words to erroneously cluster together in the embedding space. Driven by the analysis, we design a metric to detect spurious tokens and also propose a family of regularization methods, NFL (doN't Forget your Language) to mitigate spurious correlations in text classification. Experiments show that NFL can effectively prevent erroneous clusters and significantly improve the robustness of classifiers.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models2022
- P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks2022
- FewNLU: Benchmarking State-of-the-Art Methods for Few-Shot Natural Language Understanding2022
- Competency Problems: On Finding and Removing Artifacts in Language Data2021
- MedNLI Is Not Immune: Natural Language Inference Artifacts in the Clinical Domain2021
- An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language ModelsTransactions of the Association for Computational Linguistics, 2020
- Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles2020
- Identifying Spurious Correlations for Robust Text Classification2020
- Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance2020
- Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification2019