A Multi-label Multi-hop Relation Detection Model based on Relation-aware Sequence Generation

Linhai Zhang, Deyu Zhou, Chao Lin, Yulan He


Abstract
Multi-hop relation detection in Knowledge Base Question Answering (KBQA) aims at retrieving the relation path starting from the topic entity to the answer node based on a given question, where the relation path may comprise multiple relations. Most of the existing methods treat it as a single-label learning problem while ignoring the fact that for some complex questions, there exist multiple correct relation paths in knowledge bases. Therefore, in this paper, multi-hop relation detection is considered as a multi-label learning problem. However, performing multi-label multi-hop relation detection is challenging since the numbers of both the labels and the hops are unknown. To tackle this challenge, multi-label multi-hop relation detection is formulated as a sequence generation task. A relation-aware sequence relation generation model is proposed to solve the problem in an end-to-end manner. Experimental results show the effectiveness of the proposed method for relation detection and KBQA.
Anthology ID:
2021.findings-emnlp.404
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4713–4719
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.404
DOI:
10.18653/v1/2021.findings-emnlp.404
Bibkey:
Cite (ACL):
Linhai Zhang, Deyu Zhou, Chao Lin, and Yulan He. 2021. A Multi-label Multi-hop Relation Detection Model based on Relation-aware Sequence Generation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4713–4719, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
A Multi-label Multi-hop Relation Detection Model based on Relation-aware Sequence Generation (Zhang et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.404.pdf
Data
SimpleQuestions