%0 Journal Article %A Balcan, Nina %A Blum, Avrim %A Mansour, Yishay %D 2005 %T Exploiting Ontology Structures and Unlabeled Data for Learning %U https://kilthub.cmu.edu/articles/journal_contribution/Exploiting_Ontology_Structures_and_Unlabeled_Data_for_Learning/6605432 %R 10.1184/R1/6605432.v1 %2 https://kilthub.cmu.edu/ndownloader/files/12095897 %K computer sciences %X

We present and analyze a theoretical model designed to understand and explain the effectiveness of ontologies for learning multiple related tasks from primarily unlabeled data. We present both information-theoretic results as well as efficient algorithms. We show in this model that an ontology, which specifies the relationships between multiple outputs, in some cases is sufficient to completely learn a classification using a large unlabeled data source

%I Carnegie Mellon University