Knowledge retrieval and reasoning are two key stages in multi-hop question answering (QA) at web scale. Existing approaches suffer from low confidence when retrieving evidence facts to fill the knowledge gap and lack transparent reasoning process. In this paper, we propose a new framework to exploit more valid facts while obtaining explainability for multi-hop QA by dynamically constructing a semantic graph and reasoning over it. We employ Abstract Meaning Representation (AMR) as semantic graph representation. Our framework contains three new ideas: (a) {\tt AMR-SG}, an AMR-based Semantic Graph, constructed by candidate fact AMRs to uncover any hop relations among question, answer and multiple facts. (b) A novel path-based fact analytics approach exploiting {\tt AMR-SG} to extract active facts from a large fact pool to answer questions. (c) A fact-level relation modeling leveraging graph convolution network (GCN) to guide the reasoning process. Results on two scientific multi-hop QA datasets show that we can surpass recent approaches including those using additional knowledge graphs while maintaining high explainability on OpenBookQA and achieve a new state-of-the-art result on ARC-Challenge in a computationally practicable setting.
翻译:知识检索和推理是网上多点答题(QA)的两个关键阶段。在检索证据事实以填补知识差距和缺乏透明推理过程时,现有方法缺乏信心。在本文件中,我们提出一个新的框架,以便利用更有效的事实,同时通过动态构建语义图和推理,为多点答题(QA)获得解释性解释性多点答题。我们使用抽象表示式(AMR)作为语义图解。我们的框架包含三个新想法:(a) 以AMR为基础的一个基于AMR的语义图,即基于候选事实的语义图,以发现问题、回答和多个事实之间的任何跳动关系。(b) 一种基于路径的新式事实分析法,以探索多点答题和多个事实之间的任何跳动关系,同时利用高级事实图从一个事实库中提取积极的事实来回答问题。 (c) 一个利用图形革命网络(GCN)的事实级关系模型来指导推理过程。两个科学多点解算式QA数据集的结果表明,我们可以超越最近的方法,包括使用更多知识图表,同时保持新的可实现的A-CRCR在新的计算结果中进行新的可实现。A-C-CR-C-C-C-C-C-CR-C-C-C-CR-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C