Combining Two And Three-Way Embeddings Models for Link Prediction in Knowledge Bases

2 Jun 2015Alberto Garcia-DuranAntoine BordesNicolas UsunierYves Grandvalet

This paper tackles the problem of endogenous link prediction for Knowledge Base completion. Knowledge Bases can be represented as directed graphs whose nodes correspond to entities and edges to relationships... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.