Knowledge Base Embeddings: Semantics and Theoretical Properties - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

Knowledge Base Embeddings: Semantics and Theoretical Properties

Résumé

Research on knowledge graph embeddings has recently evolved into knowledge base embeddings, where the goal is not only to map facts into vector spaces but also constrain the models so that they take into account the relevant conceptual knowledge available. This paper examines recent methods that have been proposed to embed knowledge bases in description logic into vector spaces through the lens of their geometric-based semantics. We identify several relevant theoretical properties, which we draw from the literature and sometimes generalize or unify. We then investigate how concrete embedding methods fit in this theoretical framework.
Fichier principal
Vignette du fichier
KR2024_BouGuiKouLacOza.pdf (501.67 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04730708 , version 1 (10-10-2024)

Identifiants

  • HAL Id : hal-04730708 , version 1

Citer

Camille Bourgaux, Ricardo Guimarães, Raoul Koudijs, Victor Lacerda, Ana Ozaki. Knowledge Base Embeddings: Semantics and Theoretical Properties. KR 2024 - 21st International Conference on Principles of Knowledge Representation and Reasoning, Nov 2024, Hanoi, Vietnam. ⟨hal-04730708⟩
0 Consultations
0 Téléchargements

Partager

More