Fall 2003: CLSP Seminar Series	Tuesday, May 13, 2008

Supervised Learning without Annotated Data, and Other Sabbatical Adventures in the Making

Philip Resnik - September 9^th, 2003

University of Maryland and Johns Hopkins University

The last decade has taught computational linguists that high performance on broad-coverage NLP tasks is best obtained using supervised learning techniques, which require annotation of large quantities of training data. But annotated text is hard to obtain, especially for linguistically deeper problems such as parsing and word sense disambiguation. In this talk, I will describe one way around this difficulty that I have been exploring, taking advantage of the shared meaning hidden between the lines of sentences in parallel translation. I will also sketch out some other ideas I hope to explore while on sabbatical this year at JHU.

Biographical Information

Philip Resnik is an associate professor at the University of Maryland, with appointments in Linguistics and at the Institute for Advanced Computer Studies. His office this year is NEB 326, and if you have something interesting to chat about he very much hopes you'll stop by.

Seminar Schedule

The Center for Language and Speech Processing The Johns Hopkins University 3400 North Charles Street, Barton Hall Baltimore, MD 21218
	Telephone: (410) 516-4237		Fax: (410) 516-5050		E-mail: clsp@clsp.jhu.edu