KG-BERT: BERT for Knowledge Graph Completion

TL;DR

KG-BERT leverages pre-trained language models to improve knowledge graph completion by treating triples as textual sequences, achieving state-of-the-art results in various tasks.

Contribution

This work introduces KG-BERT, a novel framework that applies BERT to knowledge graph triples, enhancing completion tasks with a language model approach.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effective in triple classification, link prediction, and relation prediction.

Utilizes entity and relation descriptions for scoring triples.

Abstract

Knowledge graphs are important resources for many artificial intelligence tasks but often suffer from incompleteness. In this work, we propose to use pre-trained language models for knowledge graph completion. We treat triples in knowledge graphs as textual sequences and propose a novel framework named Knowledge Graph Bidirectional Encoder Representations from Transformer (KG-BERT) to model these triples. Our method takes entity and relation descriptions of a triple as input and computes scoring function of the triple with the KG-BERT language model. Experimental results on multiple benchmark knowledge graphs show that our method can achieve state-of-the-art performance in triple classification, link prediction and relation prediction tasks.