Pay More Attention to Relation Exploration for Knowledge Base Question Answering
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Pay More Attention to Relation Exploration for Knowledge Base Question Answering. / Cao, Yong; Li, Xianzhi; Liu, Huiwen; Dai, Wen; Chen, Shuai; Wang, Bin; Chen, Min; Hershcovich, Daniel.
Findings of the Association for Computational Linguistics, ACL 2023. Association for Computational Linguistics (ACL), 2023. p. 2119-2136.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Pay More Attention to Relation Exploration for Knowledge Base Question Answering
AU - Cao, Yong
AU - Li, Xianzhi
AU - Liu, Huiwen
AU - Dai, Wen
AU - Chen, Shuai
AU - Wang, Bin
AU - Chen, Min
AU - Hershcovich, Daniel
N1 - Publisher Copyright: © 2023 Association for Computational Linguistics.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85175000091&partnerID=8YFLogxK
U2 - 10.18653/v1/2023.findings-acl.133
DO - 10.18653/v1/2023.findings-acl.133
M3 - Article in proceedings
AN - SCOPUS:85175000091
SP - 2119
EP - 2136
BT - Findings of the Association for Computational Linguistics, ACL 2023
PB - Association for Computational Linguistics (ACL)
T2 - 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023
Y2 - 9 July 2023 through 14 July 2023
ER -
ID: 373549208