Ontology Embedding: A Survey of Methods, Applications and Resources

2024-06-16

arXiv.org

AI Summary

Ontology embedding research lacks systematic organization and a formal definition of semantic fidelity. This paper presents the first comprehensive survey, covering over 80 publications, and formally defines semantic fidelity for ontology embeddings. We propose a unified taxonomy comprising three methodological categories: geometric modeling (in Euclidean or hyperbolic spaces), sequential modeling (via ABox/TBox serialization), and graph propagation (e.g., R-GCN, GNNs). For the first time, we systematically unify technical developments and cross-domain application paradigms—including ontology engineering, machine learning augmentation, and life sciences. To bridge a critical tooling gap, we open-source mOWL, a novel ontology embedding library. Furthermore, we identify key challenges—such as scalability and dynamic ontology modeling—and establish both a theoretical framework and empirical benchmarks to guide future research.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Data Mining & Knowledge Management: Semantic Web
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Ontologies are widely used for representing domain knowledge and meta data, playing an increasingly important role in Information Systems, the Semantic Web, Bioinformatics and many other domains. However, logical reasoning that ontologies can directly support are quite limited in learning, approximation and prediction. One straightforward solution is to integrate statistical analysis and machine learning. To this end, automatically learning vector representation for knowledge of an ontology i.e., ontology embedding has been widely investigated. Numerous papers have been published on ontology embedding, but a lack of systematic reviews hinders researchers from gaining a comprehensive understanding of this field. To bridge this gap, we write this survey paper, which first introduces different kinds of semantics of ontologies and formally defines ontology embedding as well as its property of faithfulness. Based on this, it systematically categorizes and analyses a relatively complete set of over 80 papers, according to the ontologies they aim at and their technical solutions including geometric modeling, sequence modeling and graph propagation. This survey also introduces the applications of ontology embedding in ontology engineering, machine learning augmentation and life sciences, presents a new library mOWL and discusses the challenges and future directions.

Problem

• Systematic review of ontology embedding methods
• Applications in ontology engineering and life sciences
• Introduction of new library mOWL

Innovation

• Ontology embedding integrates statistical analysis.
• Geometric modeling enhances ontology representations.
• mOWL library supports ontology engineering applications.