Translating Embeddings for Modeling Multi-relational Data - Archive ouverte HAL
Communication Dans Un Congrès Année : 2013

Translating Embeddings for Modeling Multi-relational Data

Résumé

We consider the problem of embedding entities and relationships of multi- relational data in low-dimensional vector spaces. Our objective is to propose a canonical model which is easy to train, contains a reduced number of parameters and can scale up to very large databases. Hence, we propose TransE, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities. Despite its simplicity, this assump- tion proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases. Besides, it can be successfully trained on a large scale data set with 1M entities, 25k relationships and more than 17M training samples.
Fichier principal
Vignette du fichier
bordes13nips.pdf (249.65 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00920777 , version 1 (19-12-2013)

Identifiants

  • HAL Id : hal-00920777 , version 1

Citer

Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko. Translating Embeddings for Modeling Multi-relational Data. Neural Information Processing Systems (NIPS), Dec 2013, South Lake Tahoe, United States. pp.1-9. ⟨hal-00920777⟩
10190 Consultations
3557 Téléchargements

Partager

More