Leveraging Frequent Query Substructures to Generate Formal Queries for Complex Question Answering

TL;DR

This paper introduces SubQG, a novel method leveraging frequent query substructures to improve formal query generation for complex question answering over knowledge bases, outperforming existing methods especially on challenging questions.

Contribution

The paper presents SubQG, a new approach that uses query substructure frequency to enhance query generation, particularly for complex and long-tail questions, with limited training data.

Findings

Significantly outperforms existing methods on benchmark datasets.

Effective with limited training data and noisy linking results.

Improves query generation for complex questions.

Abstract

Formal query generation aims to generate correct executable queries for question answering over knowledge bases (KBs), given entity and relation linking results. Current approaches build universal paraphrasing or ranking models for the whole questions, which are likely to fail in generating queries for complex, long-tail questions. In this paper, we propose SubQG, a new query generation approach based on frequent query substructures, which helps rank the existing (but nonsignificant) query structures or build new query structures. Our experiments on two benchmark datasets show that our approach significantly outperforms the existing ones, especially for complex questions. Also, it achieves promising performance with limited training data and noisy entity/relation linking results.