Matching with transformers in MELT

Hertling, Sven ; Portisch, Jan ; Paulheim, Heiko

PDF
om2021_LTpaper2.pdf - Published
Download (666kB)

URL:	https://madoc.bib.uni-mannheim.de/61184
Additional URL:	http://ceur-ws.org/Vol-3063/om2021_LTpaper2.pdf
URN:	urn:nbn:de:bsz:180-madoc-611841
Document Type:	Conference or workshop publication
Year of publication:	2021
Book title:	OM 2021, Ontology Matching 2021 : Proceedings of the 16th International Workshop on Ontology Matching, co-located with the 20th International Semantic Web Conference (ISWC 2021), virtual conference, October 25, 2021
The title of a journal, publication series:	CEUR Workshop Proceedings
Volume:	3063
Page range:	13-24
Conference title:	OM 2021
Location of the conference venue:	Online
Date of the conference:	25.10.2021
Publisher:	Shvaiko, Pavel ; Euzenat, Jérôme ; Jiménez-Ruiz, Ernesto ; Hassanzadeh, Oktie ; Trojahn, Cássia
Place of publication:	Aachen, Germany
Publishing house:	RWTH Aachen
ISSN:	1613-0073
Related URLs:	https://www.researchgate.net/publication... http://ceur-ws.org/Vol-3063/ https://arxiv.org/abs/2109.07401
Publication language:	English
Institution:	School of Business Informatics and Mathematics > Data Science (Paulheim 2018-)
Pre-existing license:	Creative Commons Attribution 4.0 International (CC BY 4.0)
Subject:	004 Computer science, internet
Individual keywords (German):	Datenintegration , Semantische Integration , Ontologien , Transformer , Transformermodelle
Keywords (English):	ontology matching , transformers , matcher optimization , data integration , semantic matching
Abstract:	One of the strongest signals for automated matching of ontologies and knowledge graphs are the textual descriptions of the concepts. The methods that are typically applied (such as character- or token-based comparisons) are relatively simple, and therefore do not capture the actual meaning of the texts. With the rise of transformer-based language models, text comparison based on meaning (rather than lexical features) is possible. In this paper, we model the ontology matching task as classification problem and present approaches based on transformer models. We further provide an easy to use implementation in the MELT framework which is suited for ontology and knowledge graph matching. We show that a transformer-based filter helps to choose the correct correspondences given a high-recall alignment and already achieves a good result with simple alignment post-processing methods.
Additional information:	Online-Ressource