10.1184/R1/6605432.v1 Nina Balcan Nina Balcan Avrim Blum Avrim Blum Yishay Mansour Yishay Mansour Exploiting Ontology Structures and Unlabeled Data for Learning Carnegie Mellon University 2005 computer sciences 2005-09-01 00:00:00 Journal contribution https://kilthub.cmu.edu/articles/journal_contribution/Exploiting_Ontology_Structures_and_Unlabeled_Data_for_Learning/6605432 <p>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</p>