Improving the Robustness of QA Models to Challenge Sets with Variational Question-Answer Pair Generation
This addresses robustness issues in QA models for reading comprehension, though it is incremental as it builds on existing QAG methods.
The paper tackles the problem of QA models lacking robustness to challenge sets with different distributions from training data by proposing a variational QAG model that generates diverse QA pairs to improve training set sparsity. The result shows improved accuracy on 12 challenge sets and in-distribution accuracy.
Question answering (QA) models for reading comprehension have achieved human-level accuracy on in-distribution test sets. However, they have been demonstrated to lack robustness to challenge sets, whose distribution is different from that of training sets. Existing data augmentation methods mitigate this problem by simply augmenting training sets with synthetic examples sampled from the same distribution as the challenge sets. However, these methods assume that the distribution of a challenge set is known a priori, making them less applicable to unseen challenge sets. In this study, we focus on question-answer pair generation (QAG) to mitigate this problem. While most existing QAG methods aim to improve the quality of synthetic examples, we conjecture that diversity-promoting QAG can mitigate the sparsity of training sets and lead to better robustness. We present a variational QAG model that generates multiple diverse QA pairs from a paragraph. Our experiments show that our method can improve the accuracy of 12 challenge sets, as well as the in-distribution accuracy. Our code and data are available at https://github.com/KazutoshiShinoda/VQAG.