ViMMRC 2.0 -- Enhancing Machine Reading Comprehension on Vietnamese Literature Text

TL;DR

This paper introduces ViMMRC 2.0, a challenging Vietnamese reading comprehension dataset with a multi-stage model that improves understanding of implicit context, aiming to advance AI comprehension of Vietnamese texts.

Contribution

The paper presents a new, more difficult Vietnamese reading comprehension dataset and a multi-stage attention-based model that outperforms previous baselines.

Findings

The dataset contains 699 passages and 5,273 questions with increased difficulty.

The proposed model improves accuracy over baseline BERT models.

Understanding implicit context remains a key challenge for models.

Abstract

Machine reading comprehension has been an interesting and challenging task in recent years, with the purpose of extracting useful information from texts. To attain the computer ability to understand the reading text and answer relevant information, we introduce ViMMRC 2.0 - an extension of the previous ViMMRC for the task of multiple-choice reading comprehension in Vietnamese Textbooks which contain the reading articles for students from Grade 1 to Grade 12. This dataset has 699 reading passages which are prose and poems, and 5,273 questions. The questions in the new dataset are not fixed with four options as in the previous version. Moreover, the difficulty of questions is increased, which challenges the models to find the correct choice. The computer must understand the whole context of the reading passage, the question, and the content of each choice to extract the right answers. Hence, we propose a multi-stage approach that combines the multi-step attention network (MAN) with the natural language inference (NLI) task to enhance the performance of the reading comprehension model. Then, we compare the proposed methodology with the baseline BERTology models on the new dataset and the ViMMRC 1.0. From the results of the error analysis, we found that the challenge of the reading comprehension models is understanding the implicit context in texts and linking them together in order to find the correct answers. Finally, we hope our new dataset will motivate further research to enhance the ability of computers to understand the Vietnamese language.