Few-shot Low-resource Knowledge Graph Completion with Reinforced Task Generation

Shichao Pei, Qiannan Zhang, Xiangliang Zhang


Abstract
Despite becoming a prevailing paradigm for organizing knowledge, most knowledge graphs (KGs) suffer from the low-resource issue due to the deficiency of data sources. The enrichment of KGs by automatic knowledge graph completion is impeded by the intrinsic long-tail property of KGs. In spite of their prosperity, existing few-shot learning-based models have difficulty alleviating the impact of the long-tail issue on low-resource KGs because of the lack of training tasks. To tackle the challenging long-tail issue on low-resource KG completion, in this paper, we propose a novel few-shot low-resource knowledge graph completion framework, which is composed of three components, i.e., few-shot learner, task generator, and task selector. The key idea is to generate and then select the beneficial few-shot tasks that complement the current tasks and enable the optimization of the few-shot learner using the selected few-shot tasks. Extensive experiments conducted on several real-world knowledge graphs validate the effectiveness of our proposed method.
Anthology ID:
2023.findings-acl.455
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:
7252–7264
Language:
URL:
https://aclanthology.org/2023.findings-acl.455
DOI:
10.18653/v1/2023.findings-acl.455
Bibkey:
Cite (ACL):
Shichao Pei, Qiannan Zhang, and Xiangliang Zhang. 2023. Few-shot Low-resource Knowledge Graph Completion with Reinforced Task Generation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7252–7264, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Few-shot Low-resource Knowledge Graph Completion with Reinforced Task Generation (Pei et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.455.pdf