Towards Semantically Enriched Embeddings for Knowledge Graph Completion

TL;DR

This paper discusses the integration of semantic information from description logic axioms and Large Language Models into knowledge graph embeddings to improve knowledge graph completion.

Contribution

It provides a comprehensive overview of existing KG completion algorithms, emphasizing the incorporation of semantic and type information, and suggests future research directions.

Findings

Current algorithms lack semantic understanding of schematic info

LLMs can enhance KG embeddings with semantic knowledge

Recommendations for future research in semantically enriched embeddings

Abstract

Embedding based Knowledge Graph (KG) Completion has gained much attention over the past few years. Most of the current algorithms consider a KG as a multidirectional labeled graph and lack the ability to capture the semantics underlying the schematic information. In a separate development, a vast amount of information has been captured within the Large Language Models (LLMs) which has revolutionized the field of Artificial Intelligence. KGs could benefit from these LLMs and vice versa. This vision paper discusses the existing algorithms for KG completion based on the variations for generating KG embeddings. It starts with discussing various KG completion algorithms such as transductive and inductive link prediction and entity type prediction algorithms. It then moves on to the algorithms utilizing type information within the KGs, LLMs, and finally to algorithms capturing the semantics represented in different description logic axioms. We conclude the paper with a critical reflection on the current state of work in the community and give recommendations for future directions.