%0 Generic %1 he2022machine %A He, Yuan %A Chen, Jiaoyan %A Dong, Hang %A Jiménez-Ruiz, Ernesto %A Hadian, Ali %A Horrocks, Ian %D 2022 %K bert bertmap biomedical_ontologies fma icd machine-learning ml mondo myown ncit ontology ontology-learning ontology_matching ordo relation-learning snomed subsumption umls %T Machine Learning-Friendly Biomedical Datasets for Equivalence and Subsumption Ontology Matching %U http://arxiv.org/abs/2205.03447 %X Ontology Matching (OM) plays an 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

@misc{he2022machine, abstract = {Ontology Matching (OM) plays an 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}, added-at = {2022-05-10T15:04:51.000+0200}, author = {He, Yuan and Chen, Jiaoyan and Dong, Hang and Jiménez-Ruiz, Ernesto and Hadian, Ali and Horrocks, Ian}, biburl = {https://www.bibsonomy.org/bibtex/2f79fa95d8ff5f5ac4b28c71b133d562f/hangdong}, description = {[2205.03447] Machine Learning-Friendly Biomedical Datasets for Equivalence and Subsumption Ontology Matching}, interhash = {e170ec1eafc5952e0199084aa3e70396}, intrahash = {f79fa95d8ff5f5ac4b28c71b133d562f}, keywords = {bert bertmap biomedical_ontologies fma icd machine-learning ml mondo myown ncit ontology ontology-learning ontology_matching ordo relation-learning snomed subsumption umls}, note = {cite arxiv:2205.03447}, timestamp = {2022-05-10T15:05:14.000+0200}, title = {Machine Learning-Friendly Biomedical Datasets for Equivalence and Subsumption Ontology Matching}, url = {http://arxiv.org/abs/2205.03447}, year = 2022 }