Improved Knowledge Base Completion by Path-Augmented TransR Model

TL;DR

This paper introduces PTransR, a model that enhances knowledge base completion by integrating relation path information into TransR, leading to improved link prediction accuracy.

Contribution

The paper presents PTransR, a novel path-augmented version of TransR that leverages relation paths for better knowledge base completion.

Findings

PTransR outperforms previous models in entity prediction.

Regularizing TransR with relation paths improves accuracy.

Experimental results validate the effectiveness of PTransR.

Abstract

Knowledge base completion aims to infer new relations from existing information. In this paper, we propose path-augmented TransR (PTransR) model to improve the accuracy of link prediction. In our approach, we base PTransR model on TransR, which is the best one-hop model at present. Then we regularize TransR with information of relation paths. In our experiment, we evaluate PTransR on the task of entity prediction. Experimental results show that PTransR outperforms previous models.