Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs

Ming Tu, Guangtao Wang, Jing Huang, Yun Tang, Xiaodong He, Bowen Zhou
<span title="">2019</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5n6volmnonf5tn6xputi5f2t3e" style="color: black;">Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</a> </i> &nbsp;
Multi-hop reading comprehension (RC) across documents poses new challenge over singledocument RC because it requires reasoning over multiple documents to reach the final answer. In this paper, we propose a new model to tackle the multi-hop RC problem. We introduce a heterogeneous graph with different types of nodes and edges, which is named as Heterogeneous Document-Entity (HDE) graph. The advantage of HDE graph is that it contains different granularity levels of information including
more &raquo; ... , documents and entities in specific document contexts. Our proposed model can do reasoning over the HDE graph with nodes representation initialized with co-attention and self-attention based context encoders. We employ Graph Neural Networks (GNN) based message passing algorithms to accumulate evidences on the proposed HDE graph. Evaluated on the blind test set of the Qangaroo WIKIHOP data set, our HDE graph based single model delivers competitive result, and the ensemble model achieves the state-of-the-art performance.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p19-1260">doi:10.18653/v1/p19-1260</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/acl/TuWHTHZ19.html">dblp:conf/acl/TuWHTHZ19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/os2vkhkzynh5bl2xk44yzhdpkq">fatcat:os2vkhkzynh5bl2xk44yzhdpkq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200505081107/https://www.aclweb.org/anthology/P19-1260.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9c/47/9c473e59175bd1c716824cbdfbbd8abf06f8a2a7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p19-1260"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>