Integrating Semantic Information into Sketchy Reading Module of Retro-Reader for Vietnamese Machine Reading Comprehension

TL;DR

This paper enhances the Retro-Reader model for Vietnamese machine reading comprehension by integrating semantic role labels into its encoder, leading to improved answerability classification performance.

Contribution

It introduces a novel method of incorporating semantic role labels into Retro-Reader's encoder, specifically tailored for Vietnamese MRC, demonstrating improved results.

Findings

Semantic integration improves answerability classification accuracy.

Semantic role labels enhance encoder performance in Vietnamese MRC.

The improved Retro-Reader outperforms baseline models.

Abstract

Machine Reading Comprehension has become one of the most advanced and popular research topics in the fields of Natural Language Processing in recent years. The classification of answerability questions is a relatively significant sub-task in machine reading comprehension; however, there haven't been many studies. Retro-Reader is one of the studies that has solved this problem effectively. However, the encoders of most traditional machine reading comprehension models in general and Retro-Reader, in particular, have not been able to exploit the contextual semantic information of the context completely. Inspired by SemBERT, we use semantic role labels from the SRL task to add semantics to pre-trained language models such as mBERT, XLM-R, PhoBERT. This experiment was conducted to compare the influence of semantics on the classification of answerability for the Vietnamese machine reading comprehension. Additionally, we hope this experiment will enhance the encoder for the Retro-Reader model's Sketchy Reading Module. The improved Retro-Reader model's encoder with semantics was first applied to the Vietnamese Machine Reading Comprehension task and obtained positive results.