Semantic Sentence Composition Reasoning for Multi-Hop Question Answering

TL;DR

This paper introduces a semantic sentence composition reasoning approach for multi-hop question answering, combining semantic matching and sentence composition modules to improve fact retrieval and reasoning, outperforming state-of-the-art methods.

Contribution

The paper proposes a novel multi-stage semantic matching and sentence composition framework to enhance multi-hop question answering performance.

Findings

Outperforms existing SOTA on QASC with about 9% improvement

Effectively incorporates pre-trained language models

Provides more comprehensive contextual information

Abstract

Due to the lack of insufficient data, existing multi-hop open domain question answering systems require to effectively find out relevant supporting facts according to each question. To alleviate the challenges of semantic factual sentences retrieval and multi-hop context expansion, we present a semantic sentence composition reasoning approach for a multi-hop question answering task, which consists of two key modules: a multi-stage semantic matching module (MSSM) and a factual sentence composition module (FSC). With the combination of factual sentences and multi-stage semantic retrieval, our approach can provide more comprehensive contextual information for model training and reasoning. Experimental results demonstrate our model is able to incorporate existing pre-trained language models and outperform the existing SOTA method on the QASC task with an improvement of about 9%.