Speaker: Thorsten Joachims, Computer Science, Cornell University

Date: Wednesday, March 10, 2004 4:15-5:15p

Location: Cornell Information Science, 301 College Avenue, Seminar Room

Abstract -

Over the last decade, much of the research in machine learning has focused on problems like classification and regression, where the prediction is a single discrete or real value. But what if we need to predict complex objects like trees, partitions, or orderings? Such problems arise, for example, in information retrieval, where a search engine tries to predict what is the best ranking to present to a user for a given query. Similarly, in natural language understanding a parser needs to predict the correct parse tree for a given sentence. In this talk, I will introduce a class of such problems that can be solved using a new support vector method. In particular, I will explore how this might relate to other machine learning problems in information science.

Bio -

Thorsten Joachims is an Assistant Professor in the Department of Computer Science at Cornell University . In 2001 he finished his Ph. D. as a student of Prof. Morik at the AI-unit of the University of Dortmund , from where he also received a Diplom in Computer Science in 1997. Between 2000 and 2001 he worked as a PostDoc at the GMD in the Knowledge Discovery Team of the Institute for Autonomous Intelligent Systems. From 1994 to 1996 he spent one and a half years at Carnegie Mellon University as a visiting scholar of Prof. Tom Mitchell.