Exploiting Reasoning Chains for Multi-hop Science Question Answering

TL;DR

This paper introduces a Chain Guided Retriever-reader framework that models explainable multi-hop reasoning for science question answering without needing corpus-specific annotations, improving interpretability and performance.

Contribution

It presents a novel reasoning chain generation method using semantic graphs and a chain-aware loss, enabling explainable reasoning without human-annotated chains.

Findings

Effective on OpenBookQA and ARC-Challenge datasets

Enhances explainability of multi-hop reasoning

Improves retrieval and reasoning accuracy

Abstract

We propose a novel Chain Guided Retriever-reader ({\tt CGR}) framework to model the reasoning chain for multi-hop Science Question Answering. Our framework is capable of performing explainable reasoning without the need of any corpus-specific annotations, such as the ground-truth reasoning chain, or human-annotated entity mentions. Specifically, we first generate reasoning chains from a semantic graph constructed by Abstract Meaning Representation of retrieved evidence facts. A \textit{Chain-aware loss}, concerning both local and global chain information, is also designed to enable the generated chains to serve as distant supervision signals for training the retriever, where reinforcement learning is also adopted to maximize the utility of the reasoning chains. Our framework allows the retriever to capture step-by-step clues of the entire reasoning process, which is not only shown to be effective on two challenging multi-hop Science QA tasks, namely OpenBookQA and ARC-Challenge, but also favors explainability.