Dynamically Fused Graph Network for Multi-hop Reasoning

TL;DR

This paper introduces DFGN, a novel dynamic graph-based model that enhances multi-hop reasoning in text-based question answering by dynamically exploring and fusing evidence across multiple documents, leading to interpretable reasoning chains.

Contribution

The paper presents DFGN, a new method that dynamically constructs and explores entity graphs for multi-hop reasoning, improving interpretability and reasoning over scattered evidence.

Findings

DFGN achieves competitive results on HotpotQA.

DFGN produces interpretable reasoning chains.

Dynamic fusion enhances multi-hop reasoning capabilities.

Abstract

Text-based question answering (TBQA) has been studied extensively in recent years. Most existing approaches focus on finding the answer to a question within a single paragraph. However, many difficult questions require multiple supporting evidence from scattered text among two or more documents. In this paper, we propose Dynamically Fused Graph Network(DFGN), a novel method to answer those questions requiring multiple scattered evidence and reasoning over them. Inspired by human's step-by-step reasoning behavior, DFGN includes a dynamic fusion layer that starts from the entities mentioned in the given query, explores along the entity graph dynamically built from the text, and gradually finds relevant supporting entities from the given documents. We evaluate DFGN on HotpotQA, a public TBQA dataset requiring multi-hop reasoning. DFGN achieves competitive results on the public board. Furthermore, our analysis shows DFGN produces interpretable reasoning chains.