Neighborhood Mixture Model for Knowledge Base Completion

TL;DR

This paper introduces a neighborhood mixture model that enhances knowledge base completion by integrating local neighborhood information into entity representations, significantly improving upon existing embedding methods.

Contribution

It proposes a novel entity representation method combining neighborhood data with TransE, leading to improved knowledge base completion performance.

Findings

Neighborhood information improves TransE results

Outperforms state-of-the-art models on benchmarks

Enhances triple classification and prediction tasks

Abstract

Knowledge bases are useful resources for many natural language processing tasks, however, they are far from complete. In this paper, we define a novel entity representation as a mixture of its neighborhood in the knowledge base and apply this technique on TransE-a well-known embedding model for knowledge base completion. Experimental results show that the neighborhood information significantly helps to improve the results of the TransE model, leading to better performance than obtained by other state-of-the-art embedding models on three benchmark datasets for triple classification, entity prediction and relation prediction tasks.