A Divide-And-Conquer Approach for Multi-label Multi-hop Relation Detection in Knowledge Base Question Answering

Deyu Zhou, Yanzheng Xiang, Linhai Zhang, Chenchen Ye, Qian-Wen Zhang, Yunbo Cao


Abstract
Relation detection in knowledge base question answering, aims to identify the path(s) of relations starting from the topic entity node that is linked to the answer node in knowledge graph. Such path might consist of multiple relations, which we call multi-hop. Moreover, for a single question, there may exist multiple relation paths to the correct answer, which we call multi-label. However, most of existing approaches only detect one single path to obtain the answer without considering other correct paths, which might affect the final performance. Therefore, in this paper, we propose a novel divide-and-conquer approach for multi-label multi-hop relation detection (DC-MLMH) by decomposing it into head relation detection and conditional relation path generation. In specific, a novel path sampling mechanism is proposed to generate diverse relation paths for the inference stage. A majority-vote policy is employed to detect final KB answer. Comprehensive experiments were conducted on the FreebaseQA benchmark dataset. Experimental results show that the proposed approach not only outperforms other competitive multi-label baselines, but also has superiority over some state-of-art KBQA methods.
Anthology ID:
2021.findings-emnlp.412
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4798–4808
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.412
DOI:
10.18653/v1/2021.findings-emnlp.412
Bibkey:
Cite (ACL):
Deyu Zhou, Yanzheng Xiang, Linhai Zhang, Chenchen Ye, Qian-Wen Zhang, and Yunbo Cao. 2021. A Divide-And-Conquer Approach for Multi-label Multi-hop Relation Detection in Knowledge Base Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4798–4808, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
A Divide-And-Conquer Approach for Multi-label Multi-hop Relation Detection in Knowledge Base Question Answering (Zhou et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.412.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.412.mp4
Data
SimpleQuestions