Knowledge Graph Refinement based on Triplet BERT-Networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Knowledge Graph Refinement based on Triplet BERT-Networks

Résumé

Knowledge graph embedding techniques are widely used for knowledge graph refinement tasks such as graph completion and triple classification. These techniques aim at embedding the entities and relations of a Knowledge Graph (KG) in a low dimensional continuous feature space. This paper adopts a transformer-based triplet network creating an embedding space that clusters the information about an entity or relation in the KG. It creates textual sequences from facts and fine-tunes a triplet network of pre-trained transformer-based language models. It adheres to an evaluation paradigm that relies on an efficient spatial semantic search technique. We show that this evaluation protocol is more adapted to a few-shot setting for the relation prediction task. Our proposed GilBERT method is evaluated on triplet classification and relation prediction tasks on multiple well-known benchmark knowledge graphs such as FB13, WN11, and FB15K. We show that GilBERT achieves better or comparable results to the state-of-theart performance on these two refinement tasks.
Fichier non déposé

Dates et versions

hal-03950704 , version 1 (22-01-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-03950704 , version 1

Citer

Armita Khajeh Nassiri, Nathalie Pernelle, Fatiha Saïs, Gianluca Quercini. Knowledge Graph Refinement based on Triplet BERT-Networks. Deep Learning meets Ontologies and Natural Language Processing, May 2022, Hersonissos, Greece. ⟨hal-03950704⟩
56 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More