A Survey on Knowledge Graph Embeddings with Literals: Which model links better Literal-ly?

TL;DR

This survey reviews and compares various knowledge graph embedding models that incorporate literals like text and images, analyzing their theoretical foundations and empirical performance in link prediction tasks.

Contribution

It provides a comprehensive overview and comparison of KG embedding models with literals, including theoretical analysis and empirical evaluation under uniform conditions.

Findings

Certain models outperform others in link prediction accuracy.

Inclusion of literals enhances embedding quality.

Empirical results highlight the strengths and weaknesses of different approaches.

Abstract

Knowledge Graphs (KGs) are composed of structured information about a particular domain in the form of entities and relations. In addition to the structured information KGs help in facilitating interconnectivity and interoperability between different resources represented in the Linked Data Cloud. KGs have been used in a variety of applications such as entity linking, question answering, recommender systems, etc. However, KG applications suffer from high computational and storage costs. Hence, there arises the necessity for a representation able to map the high dimensional KGs into low dimensional spaces, i.e., embedding space, preserving structural as well as relational information. This paper conducts a survey of KG embedding models which not only consider the structured information contained in the form of entities and relations in a KG but also the unstructured information represented as literals such as text, numerical values, images, etc. Along with a theoretical analysis and comparison of the methods proposed so far for generating KG embeddings with literals, an empirical evaluation of the different methods under identical settings has been performed for the general task of link prediction.