Entity Embedding Analogy for Implicit Link Discovery - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année :

Entity Embedding Analogy for Implicit Link Discovery

(1) , (1) ,
Nada Mimouni
Jean-Claude Jc Moissinac
Anh Tuan Vu
  • Fonction : Auteur
  • PersonId : 1053524


In this work we are interested in the problem of knowledge graphs (KG) incompleteness that we propose to solve by discovering implicit triples using observed ones in the incomplete graph leveraging analogy structures deducted from KG embedding model. We use a language modelling approach that we adapt to entities and relations. The first results show that analogical inferences in the projected vector space is relevant for link prediction task.
Fichier principal
Vignette du fichier
ESWC_Poster.pdf (314.25 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02281145 , version 1 (09-09-2019)


  • HAL Id : hal-02281145 , version 1


Nada Mimouni, Jean-Claude Jc Moissinac, Anh Tuan Vu. Entity Embedding Analogy for Implicit Link Discovery. ESWC 2019, Jun 2019, Portoroz, Slovenia. ⟨hal-02281145⟩
44 Consultations
163 Téléchargements


Gmail Facebook Twitter LinkedIn More