The GeneralRelation track evaluates ontology matching systems on their ability to detect general semantic relations beyond simple equivalence. This better reflects real-world ontology alignment scenarios, where ontologies may differ in structure, granularity, and classification perspective.
Five mutually disjoint relation types are included:
This track addresses the need for alignment approaches capable of capturing nuanced relationships, enabling richer semantic integration for tasks such as knowledge graph merging, master data integration, and semantic search.
The benchmark dataset suite is publicly available via Zenodo:
The datasets come from three major sources: Product Classification Standards (ETIM, eClass, UNSPSC, GPC), STROMA/TaSeR Test Cases, and Modified OAEI Testcases. They vary in size, structure, and semantic complexity, and all reference alignments are annotated with explicit relation types.
Source | Dataset | # Source Classes | # Target Classes | # Source Properties | # Target Properties | ≡ | ≥ | ≤ | ≈ |
---|---|---|---|---|---|---|---|---|---|
Product Classification Standards | GPC–UNSPSC | 1,151 | 30,707 | 839 | 3 | 255 | 1,377 | 250 | 17,738 |
GPC–UNSPSC+ | 5,342 | 30,707 | 839 | 3 | 381 | 3,306 | 1293 | 23,600 | |
STROMA/TaSeR Test Cases | g1–web | 728 | 1,132 | 0 | 0 | 175 | 26 | 29 | — |
g2–diseases | 1,109 | 5,146 | 0 | 0 | 316 | 11 | 27 | — | |
g3–text | 335 | 260 | 0 | 0 | 70 | 267 | 425 | — | |
g5–groceries | 60 | 335 | 0 | 0 | 29 | 113 | 14 | — | |
g7–literature | 41 | 155 | 0 | 0 | 12 | 52 | 18 | — | |
Modified OAEI Testcases | Anatomy* | 2,441 | 2,773 | 3 | 2 | 676 | 671 | 600 | — |
For inquiries or to request evaluation support, please contact the track organizers:
Xianhao Liu (xliu@stibosystems.com),
Sven Hertling (sven.hertling@uni-mannheim.de),
Michael R. Hansen (mire@dtu.com)