Multi-hop reading comprehension (MHRC) requires not only to predict the correct answer span in the given passage, but also to provide a chain of supporting evidences for reasoning interpretability. It is natural to model such a process into graph structure by understanding multi-hop reasoning as jumping over entity nodes, which has made graph modelling dominant on this task. Recently, there have been dissenting voices about whether graph modelling is indispensable due to the inconvenience of the graph building, however existing state-of-the-art graph-free attempts suffer from huge performance gap compared to graph-based ones. This work presents a novel graph-free alternative which firstly outperform all graph models on MHRC. In detail, we exploit a select-to-guide (S2G) strategy to accurately retrieve evidence paragraphs in a coarse-to-fine manner, incorporated with two novel attention mechanisms, which surprisingly shows conforming to the nature of multi-hop reasoning. Our graph-free model achieves significant and consistent performance gain over strong baselines and the current new state-of-the-art on the MHRC benchmark, HotpotQA, among all the published works.
翻译:多点阅读理解(MHRC)不仅需要预测特定段落的正确答案范围,还需要提供一系列辅助性证据,以便进行推理解释。通过理解多点跳过实体节点的多点推理,将这一过程建成图表结构是自然而然的。最近,由于图形模型模型的不便,人们对于图形模型是否必不可少有不同意见,然而,与基于图形的模型相比,现有最先进的无图表尝试存在巨大的性能差距。这项工作提出了一个新的无图表替代方法,首先优于MHRC的所有图形模型。我们详细利用选择到指导(S2G)战略,以粗略到纯度的方式准确检索证据段落,并结合两个新颖的关注机制,令人惊讶地表明与多点推理的性质相符。我们的无图表模型在强大的基线和目前有关MHRC基准的新状态,即HotpotQA,在所有出版的作品中取得了显著和一致的业绩收益。