Composing Relationships with Translations - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Composing Relationships with Translations

Résumé

Performing link prediction in Knowledge Bases (KBs) with embedding-based models , like with the model TransE (Bordes et al., 2013) which represents relationships as translations in the embedding space, have shown promising results in recent years. Most of these works focused on modeling single relationships and hence do not take full advantage of the graph structure of KBs. In this paper, we propose an extension of TransE that learns to explicitly model composition of relationships via the addition of their corresponding translation vectors. We show empirically that this allows to improve performance for predicting single relationships as well as compositions of pairs of them.
Fichier principal
Vignette du fichier
emnlp2015.pdf (179.65 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01301243 , version 1 (11-04-2016)

Identifiants

Citer

Alberto García-Durán, Antoine Bordes, Nicolas Usunier. Composing Relationships with Translations. Conference on Empirical Methods in Natural Language Processing (EMNLP 2015), Sep 2015, Lisbonne, Portugal. pp.286-290, ⟨10.18653/v1/D15-1034⟩. ⟨hal-01301243⟩
101 Consultations
93 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More