Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering

TL;DR

This paper introduces a dynamic semantic graph framework using AMR for explainable multi-hop science question answering, improving evidence retrieval and reasoning transparency over existing methods.

Contribution

It presents a novel AMR-based semantic graph construction, path-based fact analysis, and GCN-guided reasoning for enhanced multi-hop QA explainability and accuracy.

Findings

Outperforms recent approaches on scientific QA datasets.

Achieves state-of-the-art results on ARC-Challenge.

Maintains high explainability in reasoning process.

Abstract

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.