Ontology Matching (OM) playsan important role in many domains such as bioinformatics and the Semantic Web, and its research is becoming increasingly popular, especially with the application of machine learning (ML) techniques. Although the Ontology Alignment Evaluation Initiative (OAEI) represents an impressive effort for the systematic evaluation of OM systems, it still suffers from several limitations including limited evaluation of subsumption mappings, suboptimal reference mappings, and limited support for the evaluation of ML-based systems. To tackle these limitations, we introduce five new biomedical OM tasks involving ontologies extracted from Mondo and UMLS. Each task includes both equivalence and subsumption matching; the quality of reference mappings is ensured by human curation, ontology pruning, etc.; and a comprehensive evaluation framework is proposed to measure OM performance from various perspectives for both ML-based and non-ML-based OM systems. We report evaluation results for OM systems of different types to demonstrate the usage of these resources, all of which are publicly available as part of the new Bio-ML track at OAEI 2022.
%0 Conference Paper
%1 10.1007/978-3-031-19433-7_33
%A He, Yuan
%A Chen, Jiaoyan
%A Dong, Hang
%A Jiménez-Ruiz, Ernesto
%A Hadian, Ali
%A Horrocks, Ian
%B The Semantic Web -- ISWC 2022
%C Cham
%D 2022
%E Sattler, Ulrike
%E Hogan, Aidan
%E Keet, Maria
%E Presutti, Valentina
%E Almeida, João Paulo A.
%E Takeda, Hideaki
%E Monnin, Pierre
%E Pirrò, Giuseppe
%E d'Amato, Claudia
%I Springer International Publishing
%K biomedical_ontologies doid equivalence-relations fma machine-learning ml mondo myown ontology ontology-matching ontology_mapping subsumption_relations umls
%P 575--591
%T Machine Learning-Friendly Biomedical Datasets for Equivalence and Subsumption Ontology Matching
%X Ontology Matching (OM) playsan important role in many domains such as bioinformatics and the Semantic Web, and its research is becoming increasingly popular, especially with the application of machine learning (ML) techniques. Although the Ontology Alignment Evaluation Initiative (OAEI) represents an impressive effort for the systematic evaluation of OM systems, it still suffers from several limitations including limited evaluation of subsumption mappings, suboptimal reference mappings, and limited support for the evaluation of ML-based systems. To tackle these limitations, we introduce five new biomedical OM tasks involving ontologies extracted from Mondo and UMLS. Each task includes both equivalence and subsumption matching; the quality of reference mappings is ensured by human curation, ontology pruning, etc.; and a comprehensive evaluation framework is proposed to measure OM performance from various perspectives for both ML-based and non-ML-based OM systems. We report evaluation results for OM systems of different types to demonstrate the usage of these resources, all of which are publicly available as part of the new Bio-ML track at OAEI 2022.
%@ 978-3-031-19433-7
@inproceedings{10.1007/978-3-031-19433-7_33,
abstract = {Ontology Matching (OM) playsan important role in many domains such as bioinformatics and the Semantic Web, and its research is becoming increasingly popular, especially with the application of machine learning (ML) techniques. Although the Ontology Alignment Evaluation Initiative (OAEI) represents an impressive effort for the systematic evaluation of OM systems, it still suffers from several limitations including limited evaluation of subsumption mappings, suboptimal reference mappings, and limited support for the evaluation of ML-based systems. To tackle these limitations, we introduce five new biomedical OM tasks involving ontologies extracted from Mondo and UMLS. Each task includes both equivalence and subsumption matching; the quality of reference mappings is ensured by human curation, ontology pruning, etc.; and a comprehensive evaluation framework is proposed to measure OM performance from various perspectives for both ML-based and non-ML-based OM systems. We report evaluation results for OM systems of different types to demonstrate the usage of these resources, all of which are publicly available as part of the new Bio-ML track at OAEI 2022.},
added-at = {2022-10-21T10:45:56.000+0200},
address = {Cham},
author = {He, Yuan and Chen, Jiaoyan and Dong, Hang and Jim{\'e}nez-Ruiz, Ernesto and Hadian, Ali and Horrocks, Ian},
biburl = {https://www.bibsonomy.org/bibtex/27b9244e0fb56a9e5d8371a85b70f2fbe/hangdong},
booktitle = {The Semantic Web -- ISWC 2022},
editor = {Sattler, Ulrike and Hogan, Aidan and Keet, Maria and Presutti, Valentina and Almeida, Jo{\~a}o Paulo A. and Takeda, Hideaki and Monnin, Pierre and Pirr{\`o}, Giuseppe and d'Amato, Claudia},
interhash = {079c4fc10dfe457f9a88b9a012c32902},
intrahash = {7b9244e0fb56a9e5d8371a85b70f2fbe},
isbn = {978-3-031-19433-7},
keywords = {biomedical_ontologies doid equivalence-relations fma machine-learning ml mondo myown ontology ontology-matching ontology_mapping subsumption_relations umls},
pages = {575--591},
publisher = {Springer International Publishing},
timestamp = {2022-10-21T10:46:14.000+0200},
title = {Machine Learning-Friendly Biomedical Datasets for Equivalence and Subsumption Ontology Matching},
year = 2022
}