Entity Embedding Analogy for Implicit Link Discovery - Télécom Paris Access content directly
Conference Papers Year : 2019

Entity Embedding Analogy for Implicit Link Discovery

Nada Mimouni
Jean-Claude Jc Moissinac
Anh Tuan Vu
  • Function : Author
  • PersonId : 1053524

Abstract

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
Origin : Files produced by the author(s)
Loading...

Dates and versions

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

Identifiers

  • HAL Id : hal-02281145 , version 1

Cite

Nada Mimouni, Jean-Claude Jc Moissinac, Anh Tuan Vu. Entity Embedding Analogy for Implicit Link Discovery. ESWC 2019, Jun 2019, Portoroz, Slovenia. ⟨hal-02281145⟩
56 View
187 Download

Share

Gmail Facebook X LinkedIn More