An Interpretable Knowledge Transfer Model for Knowledge Base Completion

meeting of the association for computational linguistics, 2017.

Cited by: 45|Bibtex|Views53|Links
EI

Abstract:

Knowledge bases are important resources for a variety of natural language processing tasks but suffer from incompleteness. We propose a novel embedding model, emph{ITransF}, to perform knowledge base completion. Equipped with a sparse attention mechanism, ITransF discovers hidden concepts of relations and transfer statistical strength thr...More

Code:

Data:

Your rating :
0

 

Tags
Comments