Communication Dans Un Congrès Année : 2026

Unsupervised Linking of Unstructured Data Entities to a Knowledge Graph

Résumé

Recently, Large Language Models (LLM) have been used to generate structured graph data from unstructured text. However, parts of the extracted nodes lack information and retraining is necessary whenever the graph changes. We propose an unsupervised approach based on embeddings similarity, to link entities extracted by a LLM from unstructured text data to nodes of a knowledge graph, generated according to an ontology. Tested on three datasets from a maritime cyber security use case, results indicate an accuracy improvement from 86.2% up to 91,4%, depending on the number of neighbors and context candidate nodes.

Fichier principal
Vignette du fichier
Papier_IJCKG_2025_F.pdf (360.83 Ko) Télécharger le fichier

Dates et versions

hal-05584627 , version 1 (08-04-2026)

Licence

Identifiants

Citer

Gabriel Dumont, Pedro Merino-Laso, John Puentes. Unsupervised Linking of Unstructured Data Entities to a Knowledge Graph. Knowledge Graphs. 14th International Joint Conference, IJCKG 2025, Oct 2025, Heraklion, Crete, Greece. pp.430-436, ⟨10.1007/978-981-95-5009-8_29⟩. ⟨hal-05584627⟩
110 Consultations
31 Téléchargements

Altmetric

Partager

  • More