An Interpretable Knowledge Transfer Model for Knowledge Base Completion
This work addresses knowledge base completion for natural language processing tasks, offering an interpretable method with competitive performance, though it appears incremental as it builds on existing embedding models.
The paper tackles the problem of incompleteness in knowledge bases by proposing ITransF, a novel embedding model that uses a sparse attention mechanism to discover hidden concepts of relations and transfer statistical strength, achieving improvements in mean rank and Hits@10 metrics on WN18 and FB15k datasets.
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 through the sharing of concepts. Moreover, the learned associations between relations and concepts, which are represented by sparse attention vectors, can be interpreted easily. We evaluate ITransF on two benchmark datasets---WN18 and FB15k for knowledge base completion and obtains improvements on both the mean rank and Hits@10 metrics, over all baselines that do not use additional information.