Generative Relation Linking for Question Answering over Knowledge Bases

TL;DR

This paper introduces a generative approach to relation linking in question answering over knowledge bases, leveraging pre-trained sequence-to-sequence models with structured data infusion to improve accuracy and adaptability.

Contribution

It presents a novel generative method for relation linking that incorporates structured knowledge base data, outperforming existing systems with a simpler, adaptable model.

Findings

Significant performance improvements over state-of-the-art methods.

Effective handling of knowledge base nuances through data infusion.

Model adaptability across multiple datasets from DBpedia and Wikidata.

Abstract

Relation linking is essential to enable question answering over knowledge bases. Although there are various efforts to improve relation linking performance, the current state-of-the-art methods do not achieve optimal results, therefore, negatively impacting the overall end-to-end question answering performance. In this work, we propose a novel approach for relation linking framing it as a generative problem facilitating the use of pre-trained sequence-to-sequence models. We extend such sequence-to-sequence models with the idea of infusing structured data from the target knowledge base, primarily to enable these models to handle the nuances of the knowledge base. Moreover, we train the model with the aim to generate a structured output consisting of a list of argument-relation pairs, enabling a knowledge validation step. We compared our method against the existing relation linking systems on four different datasets derived from DBpedia and Wikidata. Our method reports large improvements over the state-of-the-art while using a much simpler model that can be easily adapted to different knowledge bases.