Composing Relationships with Translations

• DOI: 10.18653/v1/d15-1034
• Publication Date: 2015-12-15T11:53:04Z
• Authors: Alberto Garcia-Duran; Antoine Bordes; Nicolas Usunier
• Keywords: Knowledge graph; Link (geometry)

Performing link prediction in Knowledge Bases (KBs) with embedding-based models, like the model TransE (Bordes et al., 2013) which represents relationships as translations embedding space, have shown promising results recent years.Most of these works are focused on modeling single and hence do not take full advantage graph structure KBs.In this paper, we propose an extension that learns to explicitly composition via addition their corresponding translation vectors.We show empirically allows improve performance for predicting well compositions pairs them.