EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-level Shared Knowledge Guided Learning for Knowledge Graph Completion

Yongxue Shan, Jie Zhou, Jie Peng, Xin Zhou, Jiaqian Yin, Xiaodong Wang

Transactions of the Association for Computational Linguistics · 04.09.2024 · 12 · 1027-1042

DOI: 10.1162/tacl_a_00686 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 04.09.2024. Verfasst von Yongxue Shan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the task of Knowledge Graph Completion (KGC), the existing datasets and their inherent subtasks carry a wealth of shared knowledge that can be utilized to enhance the representation of knowledge triplets and overall performance. However, no current studies specifically address the shared knowledge within KGC. To bridge this gap, we introduce a multi-level Shared Knowledge Guided learning method (SKG) that operates at both the dataset and task levels. On the dataset level, SKG-KGC broadens the original dataset by identifying shared features within entity sets via text summarization. On the task level, for the three typical KGC subtasks—head entity prediction, relation prediction, and tail entity prediction—we present an innovative multi-task learning architecture with dynamically adjusted loss weights. This approach allows the model to focus on more challenging and underperforming tasks, effectively mitigating the imbalance of knowledge sharing among subtasks. Experimental results demonstrate that SKG-KGC outperforms existing text-based methods significantly on three well-known datasets, with the most notable improvement on WN18RR (MRR: 66.6%→ 72.2%, Hit@1: 58.7%→67.0%).

Zitieren

APA

Shan, Y., Zhou, J., Peng, J., Zhou, X., Yin, J., & Wang, X. (2024). Multi-level Shared Knowledge Guided Learning for Knowledge Graph Completion. Transactions of the Association for Computational Linguistics, 12, 1027-1042. https://doi.org/10.1162/tacl_a_00686

Vancouver

Shan Y, Zhou J, Peng J, Zhou X, Yin J, Wang X. Multi-level Shared Knowledge Guided Learning for Knowledge Graph Completion. Transactions of the Association for Computational Linguistics. 2024;12:1027-1042. doi:10.1162/tacl_a_00686

BibTeX
@article{Shan2024,
  author = {Shan, Yongxue and Zhou, Jie and Peng, Jie and Zhou, Xin and Yin, Jiaqian and Wang, Xiaodong},
  title = {Multi-level Shared Knowledge Guided Learning for Knowledge Graph Completion},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2024},
  volume = {12},
  pages = {1027--1042},
  doi = {10.1162/tacl_a_00686}
}
Kostenlos starten →