Does Data Augmentation Improve Generalization in NLP?

Neural models often exploit superficial features to achieve good performance, rather than deriving more general features. Overcoming this tendency is a central challenge in areas such as representation learning and ML fairness. Recent work has proposed using data augmentation, i.e., generating training examples where the superficial features fail, as a means of encouraging models to prefer the stronger features. We design a series of toy learning problems to test the hypothesis that data augmentation leads models to unlearn weaker heuristics, but not to learn stronger features in their place. We find partial support for this hypothesis: Data augmentation often hurts before it helps, and it is less effective when the preferred strong feature is much more difficult to extract than the competing weak feature.