S-Match won inaugural ESWC 7 Years Award! Read more...
Lightweight ontologies provide the formal representation to be able to reason about hierarchical structures such as classifications. Each node's label in the classification is translated into propositional description logic (DL) formula, which univocally codifies the meaning of the node.
Evaluating and comparing different semantic matching techniques is a complex multifaceted problem. Currently, various practices are used for evaluations and many of them rely on golden standards. Here we provide several such datasets for evaluating various aspects of semantic matching algorithms.
Background Knowledge Datasets
Background knowledge is the set of true facts used by semantic tools to draw their conclusions. For instance it may contain that dog is an animal or that Rome is a city and it is part of Italy. Here we provide several datasets to be used as a background knowledge for semantic matching algorithms.