A Co-Matching Model for Multi-choice Reading Comprehension

TL;DR

This paper introduces a co-matching model for multi-choice reading comprehension that jointly assesses passage-question-answer compatibility, achieving state-of-the-art results on the RACE dataset.

Contribution

It proposes a novel co-matching approach that models passage-question-answer matching simultaneously, improving performance over existing methods.

Findings

Achieves state-of-the-art accuracy on RACE dataset

Demonstrates effectiveness of joint matching approach

Outperforms previous models in multi-choice reading comprehension

Abstract

Multi-choice reading comprehension is a challenging task, which involves the matching between a passage and a question-answer pair. This paper proposes a new co-matching approach to this problem, which jointly models whether a passage can match both a question and a candidate answer. Experimental results on the RACE dataset demonstrate that our approach achieves state-of-the-art performance.