Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network [article]

Zeyun Tang, Yongliang Shen, Xinyin Ma, Wei Xu, Jiale Yu, Weiming Lu
2020 arXiv   pre-print
Multi-hop reading comprehension across multiple documents attracts much attention recently. In this paper, we propose a novel approach to tackle this multi-hop reading comprehension problem. Inspired by human reasoning processing, we construct a path-based reasoning graph from supporting documents. This graph can combine both the idea of the graph-based and path-based approaches, so it is better for multi-hop reasoning. Meanwhile, we propose Gated-RGCN to accumulate evidence on the path-based
more » ... asoning graph, which contains a new question-aware gating mechanism to regulate the usefulness of information propagating across documents and add question information during reasoning. We evaluate our approach on WikiHop dataset, and our approach achieves state-of-the-art accuracy against previously published approaches. Especially, our ensemble model surpasses human performance by 4.2%.
arXiv:2006.06478v2 fatcat:n6ryecpfa5eblocqokm2x4r5ri