Article Dans Une Revue Neurosymbolic Artificial Intelligence Année : 2025

Towards semantically enriched embeddings for knowledge graph completion

Résumé

Embedding based Knowledge Graph (KG) completion has gained much attention over the past few years. Most of the current algorithms consider a KG as a multidirectional labeled graph and lack the ability to capture the semantics underlying the schematic information. This position paper revises the state of the art and discusses several variations of the existing algorithms for KG completion, which are discussed progressively based on the level of expressivity of the semantics utilized. The paper begins with analysing various KG completion algorithms considering only factual information such as transductive and inductive link prediction and entity type prediction algorithms. It then revises the algorithms utilizing Large Language Models as background knowledge. Afterwards, it discusses the algorithms progressively utilizing semantic information such as class hierarchy information within the KGs and semantics represented in different description logic axioms. The paper concludes with a critical reflection on the current state of work in the community, where we argue that the aspects of semantics, rigorous evaluation protocols, and bias against external sources have not been sufficiently addressed in the literature, which hampers a more thorough understanding of advantages and limitations of existing approaches. Lastly, we provide recommendations for future directions.

Fichier principal
Vignette du fichier
nai_template.pdf (227.88 Ko) Télécharger le fichier
alam-et-al.tar.gz (143.65 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05113305 , version 1 (15-06-2025)

Licence

Identifiants

Citer

Mehwish Alam, Frank van Harmelen, Maribel Acosta. Towards semantically enriched embeddings for knowledge graph completion. Neurosymbolic Artificial Intelligence, 2025, 1, pp.1-16. ⟨10.3233/NAI-240731⟩. ⟨hal-05113305⟩
1497 Consultations
194 Téléchargements

Altmetric

Partager

  • More