Advanced Topics in Artificial Intelligence 
(CS 3710, ISSP 3565)
Spring 2002

Time: 		MW 2:00 PM - 03:20 PM
Place: 		LRDC 814 (seminar room)
Instructor: 	Dr. Diane Litman
		litman@cs.pitt.edu
		http://www.cs.pitt.edu/~litman

Description: Dialog Systems

Dialog systems are systems in which human users speak or type to a
computer in natural language, in order to achieve their goals.  Dialog
systems are among the few realized examples of open-ended, real-time,
goal-oriented interaction between humans and computers, and are
therefore an exciting testbed for artificial intelligence research.
Dialog systems are becoming an area of increasing interest, both in
research and in practical applications.  This course will cover
traditional knowledge-based approaches to the problem, more
recent statistical work, and fundamental papers both in AI and
possibly other disciplines.

For each class, a student presenter will be assigned to lead the
discussion of a set of papers on a given topic.  Some of the topics
will be chosen based on the interests of the registered students.
Such topics might include tutoring and call routing applications,
spoken dialog systems, spoken translation systems, repair and error
recovery, grounding, evaluation, annotation, multi-party dialog analysis
(meetings, chat), machine learning approaches, and multi-modal systems.

Requirements: In addition to leading one or more class discussions,
all students will be expected to do all the readings and participate
in the other discussions.  A project or paper will also be
required.

Prerequisites:	Natural Language Processing, OR a graduate course in
		Artificial Intelligence, OR consent of the instructor.

NOTE: The official course title is "Advanced Topics in Artificial
Intelligence."  The associated CS and ISSP course numbers are used for
many AI graduate seminars. It is okay to take this course more than
once, because the topics are different in different years.