Bio-ML: A ML-friendly Biomedical track for Equivalence and Subsumption Matching
This track presents an unified evaluation framework suitable for both ML-based and non-ML-based OM systems.
The datasets of this track are based on Mondo and the UMLS Metathesaurus.
The 2022 edition involves the following ontologies: OMIM (Online Mendelian Inheritance in Man), ORDO (Orphanet Rare Disease Ontology), NCIT (National Cancer Institute Thesaurus) and DOID (Human Disease Ontology), FMA (Foundational Model of Anatyomy) and SNOMED CT.
The 2023 edition adopts locality-based logic modules to enrich existing pruned ontologies with logical and structural context from their original versions. The added entities are annotated as "not used in alignment". A new special sub-track for Large Language Model-based OM systems, named Bio-LLM, is also introduced.
Editions
Related publications
-
Yuan He, Jiaoyan Chen, Hang Dong, Ernesto Jiménez-Ruiz, Ali Hadian, Ian Horrocks. Machine Learning-Friendly Biomedical Datasets for Equivalence and Subsumption Ontology Matching. The 21st International Semantic Web Conference (ISWC 2022, Best Resource Paper Candidate). [paper] [presentation]
-
Yuan He, Jiaoyan Chen, Hang Dong, Ian Horrocks, Carlo Allocca, Taehun Kim, and Brahmananda Sapkota. DeepOnto: A Python Package for Ontology Engineering with Deep Learning arXiv preprint (2023). [paper]
-
Yuan He, Jiaoyan Chen, Hang Dong, Ian Horrocks. Exploring Large Language Models for Ontology Alignment The 22nd International Semantic Web Conference (ISWC 2023 Posters and Demos). [paper]