Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering
This addresses the need for more reliable and interpretable multi-hop QA systems in scientific domains, representing an incremental improvement with novel method components.
The paper tackles the problem of low confidence and lack of transparency in multi-hop question answering by proposing a framework that dynamically constructs a semantic graph using Abstract Meaning Representation (AMR) and reasons over it, achieving state-of-the-art results on ARC-Challenge and high explainability on OpenBookQA.
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.