Talk Topic: Modular Approaches to Computer Programs for Language Games
Michael L. Littman, Rutgers University
March 12, 2008

Abstract
Although my main research efforts are in reinforcement learning, I have a long-standing interest in statistical approaches to the syntax and semantics of natural language. I will present a survey of efforts that address formal/informal aspects of language by developing programs that attack games people play, including quiz shows, Trivial Pursuit, "flats" (verse puzzles), SAT verbal questions, and crossword puzzles. One common theme to many of the successful programs is modularity.

Bio
Michael L. Littman directs the Rutgers Laboratory for Real-Life Reinforcement Learning (RL^3) and his research in machine learning examines algorithms for decision making under uncertainty. After earning his Ph.D. from Brown University in 1996, Littman worked as an assistant professor at Duke University, a member of technical staff in AT&T's Artificial Intelligence Principles Research Department, and is now an associate professor of computer science at Rutgers. Both Duke and Rutgers honored him with teaching awards and his research has been recognized with three best-paper awards on topics of computer crossword solving, complexity analysis of planning under uncertainty, and algorithms for efficient reinforcement learning. He has served as associate editor for three of the major journals in his field.