Exploiting Rich Syntax for Better Knowledge Base Question Answering

TL;DR

This paper introduces a syntax-aware approach for Knowledge Base Question Answering that leverages dependency paths and syntactic trees, significantly improving performance over previous sequence-based methods.

Contribution

It proposes novel methods to encode syntactic information from dependency paths and trees, enhancing question understanding in KBQA systems.

Findings

Achieves state-of-the-art results on benchmark datasets.

Effectively utilizes syntactic structures for better question encoding.

Demonstrates significant performance gains over sequence-only models.

Abstract

Recent studies on Knowledge Base Question Answering (KBQA) have shown great progress on this task via better question understanding. Previous works for encoding questions mainly focus on the word sequences, but seldom consider the information from syntactic trees.In this paper, we propose an approach to learn syntax-based representations for KBQA. First, we encode path-based syntax by considering the shortest dependency paths between keywords. Then, we propose two encoding strategies to mode the information of whole syntactic trees to obtain tree-based syntax. Finally, we combine both path-based and tree-based syntax representations for KBQA. We conduct extensive experiments on a widely used benchmark dataset and the experimental results show that our syntax-aware systems can make full use of syntax information in different settings and achieve state-of-the-art performance of KBQA.