file.pdf (371.44 kB)

Exploiting Ontology Structures and Unlabeled Data for Learning

Download (371.44 kB)
journal contribution
posted on 01.09.2005 by Nina Balcan, Avrim Blum, Yishay Mansour

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

History

Date

01/09/2005

Exports

Exports