Survey on Embedding Methods Applied to Ontology Matching
ACM Computing Surveys · 30.09.2026 · 58 (12) · 1-40
DOI: 10.1145/3805799 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 15.05.2026. Verfasst von Guilherme Santos Sousa und 2 weiteren Autor:innen. Die Arbeit nennt 144 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Ontology matching plays a critical role in data integration, knowledge discovery, and ontology merging by establishing correspondences between entities from diverse ontologies. Although traditional methods have proven effective in specific scenarios, they often struggle to capture the semantic depth and contextual nuances of ontology entities, especially when applied to large, heterogeneous, and complex ontologies. Embedding-based methods have gained prominence in recent years. Their effectiveness stems from their ability to encode semantic and contextual information into dense vector representations, which enables more robust similarity computations. This survey provides a comprehensive review of embedding-based techniques applied to ontology matching, with a focus on the schema-level of ontologies. A categorization framework is proposed that identifies the key features of the different proposals and classifies them according to the embedding type, training requirements, and context handling. In addition, this work highlights the challenges and opportunities in embedding-based ontology matching.
Zitieren
APA
Sousa, G. S., Lima, R. J., & Trojahn, C. (2026). Survey on Embedding Methods Applied to Ontology Matching. ACM Computing Surveys, 58(12), 1-40. https://doi.org/10.1145/3805799
Vancouver
Sousa GS, Lima RJ, Trojahn C. Survey on Embedding Methods Applied to Ontology Matching. ACM Computing Surveys. 2026;58(12):1-40. doi:10.1145/3805799
BibTeX
@article{Sousa2026,
author = {Sousa, Guilherme Santos and Lima, Rinaldo Jose and Trojahn, Cassia},
title = {Survey on Embedding Methods Applied to Ontology Matching},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {12},
pages = {1--40},
doi = {10.1145/3805799}
}
EUVIMED