CLJun 11, 2018
A Co-Matching Model for Multi-choice Reading Comprehension
arXiv:1806.04068v11125 citations
Originality Incremental advance
AI Analysis
This addresses reading comprehension for AI systems, but it is incremental as it builds on existing matching methods.
The paper tackled multi-choice reading comprehension by proposing a co-matching approach that jointly models passage matching with questions and answers, achieving state-of-the-art performance on the RACE dataset.
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.