Knowledge Base Completion With Analogical Inference on Context Graphs - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année :

Knowledge Base Completion With Analogical Inference on Context Graphs

(1) , (1) ,
1
Nada Mimouni
Jean-Claude Jc Moissinac
Anh Tuan Vu
  • Fonction : Auteur
  • PersonId : 1053525

Résumé

Knowledge base completion refers to the task of adding new, missing, links between entities. In this work we are interested in the problem of knowledge Graph (KG) incompleteness in general purpose knowledge bases like DBpedia and Wikidata. We propose an approach for discovering implicit triples using observed ones in the incomplete graph leveraging analogy structures deducted from a KG embedding model. We use a language modelling approach where semantic regularities between words are preserved which we adapt to entities and relations. We consider excerpts from large input graphs as a reduced and meaningful context for a set of entities of a given domain. The first results show that analogical inferences in the projected vector space is relevant to a link prediction task.
Fichier principal
Vignette du fichier
SemaPro_2019_Analogy_inference_on_context_graphsJCM06092019.pdf (231.86 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02281147 , version 1 (08-09-2019)

Identifiants

  • HAL Id : hal-02281147 , version 1

Citer

Nada Mimouni, Jean-Claude Jc Moissinac, Anh Tuan Vu. Knowledge Base Completion With Analogical Inference on Context Graphs. Semapro 2019, Sep 2019, Porto, France. ⟨hal-02281147⟩
120 Consultations
124 Téléchargements

Partager

Gmail Facebook Twitter LinkedIn More