A Co-Matching Model for 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.

6, accepted ACL 2018

References in corpus (3)

• Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
• RACE: Large-scale ReAding Comprehension Dataset From Examinations
• Dynamic Fusion Networks for Machine Reading Comprehension

Cited by in corpus (11)

• Option Comparison Network for Multiple-choice Reading Comprehension
• Dual Co-Matching Network for Multi-choice Reading Comprehension
• How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence
• Generating Distractors for Reading Comprehension Questions from Real Examinations
• Do Multi-hop Readers Dream of Reasoning Chains?
• LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning
• JEC-QA: A Legal-Domain Question Answering Dataset
• GenNet : Reading Comprehension with Multiple Choice Questions using Generation and Selection model
• Knowledge Efficient Deep Learning for Natural Language Processing
• Feudal Reinforcement Learning by Reading Manuals
• Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation