Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering
This addresses the challenge of scalable and interpretable knowledge-aware question answering for AI systems that require complex reasoning.
The paper tackles the problem of enabling question answering models to perform efficient multi-hop relational reasoning over external knowledge graphs while maintaining interpretability, proposing a multi-hop graph relation network (MHGRN) that unifies path-based methods and graph neural networks. The result demonstrates effectiveness and scalability on CommonsenseQA and OpenbookQA datasets.
Existing work on augmenting question answering (QA) models with external knowledge (e.g., knowledge graphs) either struggle to model multi-hop relations efficiently, or lack transparency into the model's prediction rationale. In this paper, we propose a novel knowledge-aware approach that equips pre-trained language models (PTLMs) with a multi-hop relational reasoning module, named multi-hop graph relation network (MHGRN). It performs multi-hop, multi-relational reasoning over subgraphs extracted from external knowledge graphs. The proposed reasoning module unifies path-based reasoning methods and graph neural networks to achieve better interpretability and scalability. We also empirically show its effectiveness and scalability on CommonsenseQA and OpenbookQA datasets, and interpret its behaviors with case studies.