Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering

TL;DR

This paper introduces RDAS, a neural model that enhances question answering over knowledge bases by integrating relation-aware subgraph structures and direction-guided reasoning, leading to improved accuracy.

Contribution

The paper proposes a novel approach that converts relations into nodes and incorporates direction information to better utilize subgraph structure in KB question answering.

Findings

Significant performance improvements on two datasets.

Effective utilization of relation and direction information.

Enhanced reasoning capabilities in KB question answering.

Abstract

Question Answering (QA) models over Knowledge Bases (KBs) are capable of providing more precise answers by utilizing relation information among entities. Although effective, most of these models solely rely on fixed relation representations to obtain answers for different question-related KB subgraphs. Hence, the rich structured information of these subgraphs may be overlooked by the relation representation vectors. Meanwhile, the direction information of reasoning, which has been proven effective for the answer prediction on graphs, has not been fully explored in existing work. To address these challenges, we propose a novel neural model, Relation-updated Direction-guided Answer Selector (RDAS), which converts relations in each subgraph to additional nodes to learn structure information. Additionally, we utilize direction information to enhance the reasoning ability. Experimental results show that our model yields substantial improvements on two widely used datasets.