DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications

TL;DR

DuReader_robust is a new Chinese dataset designed to evaluate the robustness and generalization of machine reading comprehension models in real-world scenarios, highlighting their current limitations and providing insights for future improvements.

Contribution

The paper introduces DuReader_robust, a real-world Chinese MRC dataset focusing on robustness and generalization, with natural texts and comprehensive challenge tests.

Findings

MRC models perform poorly on the challenge test set.

Existing models lack robustness and generalization in real-world scenarios.

Analysis suggests directions for future model development.

Abstract

Machine reading comprehension (MRC) is a crucial task in natural language processing and has achieved remarkable advancements. However, most of the neural MRC models are still far from robust and fail to generalize well in real-world applications. In order to comprehensively verify the robustness and generalization of MRC models, we introduce a real-world Chinese dataset -- DuReader_robust. It is designed to evaluate the MRC models from three aspects: over-sensitivity, over-stability and generalization. Comparing to previous work, the instances in DuReader_robust are natural texts, rather than the altered unnatural texts. It presents the challenges when applying MRC models to real-world applications. The experimental results show that MRC models do not perform well on the challenge test set. Moreover, we analyze the behavior of existing models on the challenge test set, which may provide suggestions for future model development. The dataset and codes are publicly available at https://github.com/baidu/DuReader.