Timezone: »

Translating Embeddings for Modeling Multi-relational Data
Antoine Bordes · Nicolas Usunier · Alberto Garcia-Duran · Jason Weston · Oksana Yakhnenko

Fri Dec 06 07:00 PM -- 11:59 PM (PST) @ Harrah's Special Events Center, 2nd Floor #None

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 assumption 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.

Author Information

Antoine Bordes (Université de Technologie de Compiègne (UTC))
Nicolas Usunier (Université de Technologie de Compiègne (UTC))
Alberto Garcia-Duran (Université de Technologie de Compiègne (UTC))
Jason Weston (Google Research)
Oksana Yakhnenko (Google Research)

More from the Same Authors