Pay More Attention to Relation Exploration for Knowledge Base Question Answering

Yong Cao, Xianzhi Li, Huiwen Liu, Wen Dai, Shuai Chen, Bin Wang, Min Chen, Daniel Hershcovich

Abstract
Knowledge base question answering (KBQA) is a challenging task that aims to retrieve correct answers from large-scale knowledge bases. Existing attempts primarily focus on entity representation and final answer reasoning, which results in limited supervision for this task. Moreover, the relations, which empirically determine the reasoning path selection, are not fully considered in recent advancements. In this study, we propose a novel framework, RE-KBQA, that utilizes relations in the knowledge base to enhance entity representation and introduce additional supervision. We explore guidance from relations in three aspects, including (1) distinguishing similar entities by employing a variational graph auto-encoder to learn relation importance; (2) exploring extra supervision by predicting relation distributions as soft labels with a multi-task scheme; (3) designing a relation-guided re-ranking algorithm for post-processing. Experimental results on two benchmark datasets demonstrate the effectiveness and superiority of our framework, improving the F1 score by 5.8% from 40.5 to 46.3 on CWQ and 5.7% from 62.8 to 68.5 on WebQSP, better or on par with state-of-the-art methods.
Anthology ID:
2023.findings-acl.133
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2119–2136
Language:
URL:
https://aclanthology.org/2023.findings-acl.133
DOI:
10.18653/v1/2023.findings-acl.133
Bibkey:
Cite (ACL):
Yong Cao, Xianzhi Li, Huiwen Liu, Wen Dai, Shuai Chen, Bin Wang, Min Chen, and Daniel Hershcovich. 2023. Pay More Attention to Relation Exploration for Knowledge Base Question Answering. In Findings of the Association for Computational Linguistics: ACL 2023, pages 2119–2136, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Pay More Attention to Relation Exploration for Knowledge Base Question Answering (Cao et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-acl.133.pdf
PDF Search