Broad Area Colloquium For AI-Geometry-Graphics-Robotics-Vision


Learning and Inference in Natural Language

Prof. Dan Roth
Department of Computer Science
University of Illinois at Urbana-Champaign
Monday, March 3, 2003, 4:15PM
TCSeq 201
http://robotics.stanford.edu/ba-colloquium/

Abstract

The talk will describe research on learning and inference in the context of natural language understanding tasks. The commonly used machine learning paradigm is concerned with learning single concepts from examples. In this framework the learner attempts to learn a single hidden function, e.g., a sense of a word in a given context, from a collection of examples. However, in many cases -- as in most natural language situations -- decisions depend on the outcomes of several different but mutually dependent classifiers. The classifiers' outcomes need to respect some constraints that could arise from the sequential nature of the data or other domain specific conditions, thus requiring a level of inference on top the predictions. I will describe a paradigm in which we address the problem of using the outcomes of several different classifiers in making coherent inferences -- those that respect constraints on the outcome of the classifiers, and demonstrate it using several examples from our work on natural language understanding.

About the Speaker

Dan Roth is an Associate Professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign and the Beckman Institute of Advanced Science and Technology (UIUC). He is a fellow of the Institute of Advanced Studies at the University of Illinois and a Willett Faculty Scholar of the College of Engineering. Prof. Roth got his B.A Summa cum laude in Mathematics from the Technion, Israel and his Ph.D in Computer Science from Harvard University in 1995. His research spans both theoretical work in learning and intelligent reasoning and work on applying learning and inference to intelligent human-computer interactions -- focusing on learning and inference for natural languages understanding related tasks. Among his awards are a best paper award in the International Joint Conference on Artificial Intelligence (IJCAI) 1999, an NSF CAREER Award, the University of Illinois award for research with undergraduate students and the Xerox Award for Faculty Research. Currently, he is the program chair of ACL'03, the main international meeting of the Association for Computational Linguistics and the natural language processing community.
Contact: bac-coordinators@cs.stanford.edu

Back to the Colloquium Page