Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints

Ran Song, Shizhu He, Shengxiang Gao, Li Cai, Kang Liu, Zhengtao Yu, Jun Zhao


Abstract
Multilingual Knowledge Graph Completion (mKGC) aim at solving queries in different languages by reasoning a tail entity thus improving multilingual knowledge graphs. Previous studies leverage multilingual pretrained language models (PLMs) and the generative paradigm to achieve mKGC. Although multilingual pretrained language models contain extensive knowledge of different languages, its pretraining tasks cannot be directly aligned with the mKGC tasks. Moreover, the majority of KGs and PLMs currently available exhibit a pronounced English-centric bias. This makes it difficult for mKGC to achieve good results, particularly in the context of low-resource languages. To overcome previous problems, this paper introduces global and local knowledge constraints for mKGC. The former is used to constrain the reasoning of answer entities , while the latter is used to enhance the representation of query contexts. The proposed method makes the pretrained model better adapt to the mKGC task. Experimental results on public datasets demonstrate that our method outperforms the previous SOTA on Hits@1 and Hits@10 by an average of 12.32% and 16.03%, which indicates that our proposed method has significant enhancement on mKGC.
Anthology ID:
2023.findings-acl.488
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:
7709–7721
Language:
URL:
https://aclanthology.org/2023.findings-acl.488
DOI:
10.18653/v1/2023.findings-acl.488
Bibkey:
Cite (ACL):
Ran Song, Shizhu He, Shengxiang Gao, Li Cai, Kang Liu, Zhengtao Yu, and Jun Zhao. 2023. Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7709–7721, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints (Song et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.488.pdf