Farspredict: A benchmark dataset for link prediction

TL;DR

This paper introduces Farspredict, a Persian knowledge graph dataset, and evaluates how its structure influences link prediction accuracy using knowledge graph embedding models, outperforming Freebase in many cases.

Contribution

The paper presents Farspredict, a new Persian knowledge graph dataset, and analyzes its impact on link prediction performance with optimized graph structure.

Findings

Farspredict outperforms Freebase in link prediction tasks

Graph structure significantly affects KGE accuracy

Optimizations improve Farspredict's functionality

Abstract

Link prediction with knowledge graph embedding (KGE) is a popular method for knowledge graph completion. Furthermore, training KGEs on non-English knowledge graph promote knowledge extraction and knowledge graph reasoning in the context of these languages. However, many challenges in non-English KGEs pose to learning a low-dimensional representation of a knowledge graph's entities and relations. This paper proposes "Farspredict" a Persian knowledge graph based on Farsbase (the most comprehensive knowledge graph in Persian). It also explains how the knowledge graph structure affects link prediction accuracy in KGE. To evaluate Farspredict, we implemented the popular models of KGE on it and compared the results with Freebase. Given the analysis results, some optimizations on the knowledge graph are carried out to improve its functionality in the KGE. As a result, a new Persian knowledge graph is achieved. Implementation results in the KGE models on Farspredict outperforming Freebases in many cases. At last, we discuss what improvements could be effective in enhancing the quality of Farspredict and how much it improves.