Pay More Attention to Relation Exploration for Knowledge Base Question Answering

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Dokumenter

  • Fulltext

    Forlagets udgivne version, 11,1 MB, PDF-dokument

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.

OriginalsprogEngelsk
TitelFindings of the Association for Computational Linguistics, ACL 2023
ForlagAssociation for Computational Linguistics (ACL)
Publikationsdato2023
Sider2119-2136
ISBN (Elektronisk)9781959429623
DOI
StatusUdgivet - 2023
Begivenhed61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 - Toronto, Canada
Varighed: 9 jul. 202314 jul. 2023

Konference

Konference61st Annual Meeting of the Association for Computational Linguistics, ACL 2023
LandCanada
ByToronto
Periode09/07/202314/07/2023
SponsorBloomberg Engineering, et al., Google Research, Liveperson, Meta, Microsoft

Bibliografisk note

Funding Information:
Thanks to the anonymous reviewers for their helpful feedback. We gratefully acknowledge the insightful suggestions from Zeqi Tan. This work is supported by the China National Natural Science Foundation No. 62202182. Yong Cao is supported by China Scholarship Council (No. 202206160052) and the Zhejiang Lab’s International Talent Fund for Young Professionals.

Publisher Copyright:
© 2023 Association for Computational Linguistics.

ID: 373549208