Communication Dans Un Congrès Année : 2025

Kastor: Fine-tuned Small Language Models for Shape-based Active Relation Extraction

Kastor: Ajustement de modèles de langue frugaux pour l'extraction de motifs RDF

Résumé

RDF pattern-based extraction is a compelling approach for fine-tuning small language models (SLMs) by focusing a relation extraction task on a specified SHACL shape. This technique enables the development of efficient models trained on limited text and RDF data. In this article, we introduce Kastor, a framework that advances this approach to meet the demands for completing and refining knowledge bases in specialized domains. Kastor reformulates the traditional validation task, shifting from single SHACL shape validation to evaluating all possible combinations of properties derived from the shape. By selecting the optimal combination for each training example, the framework significantly enhances model generalization and performance. Additionally, Kastor employs an iterative learning process to refine noisy knowledge bases, enabling the creation of robust models capable of uncovering new, relevant facts.

Fichier principal
Vignette du fichier
Kastor__Fine_tuned_Small_Language_Models_for_Shape_based_Active_Relation_Extraction_AuthorVersion.pdf (1014.34 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05078493 , version 1 (22-05-2025)

Licence

Identifiants

Citer

Celian Ringwald, Fabien Gandon, Catherine Faron, Franck Michel, Hanna Abi Akl. Kastor: Fine-tuned Small Language Models for Shape-based Active Relation Extraction. Extended Semantic Web Conference 2025, Jun 2025, Portoroz, France. ⟨10.1007/978-3-031-94575-5_6⟩. ⟨hal-05078493⟩
703 Consultations
287 Téléchargements

Altmetric

Partager

  • More