Broad Area Colloquium for Artificial Intelligence,
Geometry, Graphics, Robotics and Vision
Language games and other meaningful pursuits
Michael Littman
AT&T Labs-Research
Monday, February 11, 2002, 4:15PM
Gates B01 http://robotics.stanford.edu/ba-colloquium/
Abstract
If we could figure out how to make computers understand what
we *mean* when we communicate with them in natural language, it would
open up a world of opportunities. One way to measure and spur
progress is to evaluate computers playing language games---games that
challenge people's knowledge of language. I'll survey some attempts
over the past few years to get computers to play Trivial Pursuit,
crossword puzzles, Who Wants to Be a Millionaire, and several others.
These projects exhibit some common ideas that suggest fruitful
directions for future research.
About the Speaker
Michael Littman was a member of the Artificial Intelligence Principles
Research Department at AT&T Labs---Research. His main interests are
in the area of machine learning, examining algorithms for decision
making under uncertainty and statistical natural language processing.
He received his Ph.D. from Brown University in 1996. His work on
solving crossword puzzles by computer was awarded the outstanding
paper award at the National Conference on Artificial Intelligence in
1999, and, while an assistant professor at Duke University, he was
selected for an undergraduate teaching award in 1999.
