Knowledge Representation Learning: A Quantitative Review

TL;DR

This paper provides a comprehensive review and quantitative comparison of knowledge representation learning methods, analyzing their performance on key tasks and discussing future challenges and applications in knowledge-driven AI systems.

Contribution

It offers the first extensive quantitative analysis of KRL methods across multiple tasks, highlighting their strengths, limitations, and potential future research directions.

Findings

KRL methods vary significantly in performance across tasks

Certain models outperform others in knowledge graph completion

The review identifies key challenges and future research directions in KRL

Abstract

Knowledge representation learning (KRL) aims to represent entities and relations in knowledge graph in low-dimensional semantic space, which have been widely used in massive knowledge-driven tasks. In this article, we introduce the reader to the motivations for KRL, and overview existing approaches for KRL. Afterwards, we extensively conduct and quantitative comparison and analysis of several typical KRL methods on three evaluation tasks of knowledge acquisition including knowledge graph completion, triple classification, and relation extraction. We also review the real-world applications of KRL, such as language modeling, question answering, information retrieval, and recommender systems. Finally, we discuss the remaining challenges and outlook the future directions for KRL. The codes and datasets used in the experiments can be found in https://github.com/thunlp/OpenKE.