Sunday, 14 January 2000

Sunday, 8:00-12:00

Tutorial I: Intelligent User Interfaces
Mark Maybury, The MITRE Corporation  

Tutorial II: Designing User-Adaptive Systems
Anthony Jameson, University of Saarbrucken  

Sunday, 1:30-5:30

Tutorial III: Programming by Demonstration
Henry Lieberman, MIT Media Lab  

Tutorial IV: Animated Pedagogical Agents
W. Lewis Johnson, USC/ISI  

Tutorial descriptions

Tutorial I: Intelligent User Interfaces

Mark Maybury
Information Systems Division
MITRE
http://www.mitre.org/resources/centers/it/maybury/mark.html

Intelligent user interfaces (IUI) are human-machine interfaces that aim to improve the efficiency, effectiveness, and naturalness of human-machine interaction by representing, reasoning, and acting on models of the user, domain, task, discourse, and media (e.g., graphics, natural language, gesture). Intelligent user interfaces are multifaceted, in purpose and nature, and include capabilities for multimedia input analysis, multimedia presentation generation, and the use of user, discourse and task models to personalize and enhance interaction. An on line tutorial is available at www.mitre.org/resources/centers/advanced_info/mark.htm.

Effectively implemented and deployed, intelligent user interfaces promise many benefits. These include:

• More efficient interaction -- enabling more rapid task completion with less work.
• More effective interaction -- doing the right thing at the right time, tailoring the content and form of the interaction to the context of the user, task, dialogue
• More natural interaction -- supporting spoken, written, and gestural interaction, ideally as if interacting with a human interlocutor.

The tutorial introduces intelligent user interfaces using the following outline:

• Multimedia input analysis
• Multimedia output generation
• Interaction Management, including user and discourse models and adaptation
• Agent-based interaction
• Evaluation of intelligent user interfaces

The tutorial will include animations and demonstrations.

Mark Maybury has organised multiple international symposia, given tutorials, and published over fifty technical and tutorial articles in the area of language generation, multimedia presentation, text summarization, and intelligent multimedia information retrieval. He is editor of Intelligent Multimedia Interfaces (AAAI/MIT Press, 1993), Intelligent Multimedia Information Retrieval (AAAI/MIT Press, 1997) and co-editor of Readings on Intelligent User Interfaces (Morgan Kaufmann Press, 1998), Advances in Text Summarization (MIT Press, 1999) and Advances in Knowledge Management: Classic and Contemporary Works (MIT Press, 2001) and co-author of Information Storage and Retrieval: Theory and Implementation. 2nd Edition (Kluwer Academic, 2000). Dr. Maybury is Executive Director for of MITRE's Information Systems Division.

Tutorial II: Designing User-Adaptive Systems

Anthony Jameson
Saarland University / DFKI, Germany
http://www.cs.uni-sb.de/users/jameson/

This tutorial will give participants an active understanding of the issues that arise in the design of systems that adapt to their users - ranging from personalized e-commerce sites to context-aware alerting systems. Adaptation to users has long been an important way in which intelligent user interfaces can be intelligent. Recently, the importance of user-adaptive systems has been increasing rapidly, largely because of technological advances and the growth of the world-wide web and e-commerce.

Features of the tutorial:

• Learn about the potential benefits and limitations of many forms of user-adaptation
• Discuss specific examples of deployed user-adaptive systems and current research prototypes
• Actively deal with the central issues that arise in the design of such systems by addressing them in the context of a typical design task

This tutorial is based on a conceptual framework that was introduced in tutorials at UM99 and IJCAI99. It has been extensively updated and adapted to the interests of the IUI 2001 audience. The tutorial is designed to be interesting and useful for all IUI 2001 attendees. No specific background knowledge is presupposed. The presentation will consist of lectures that refer to concrete system examples within a unifying conceptual framework, interleaved with brief discussions of an example design problem.

Anthony Jameson is a senior researcher at Saarland University and at DFKI (German Research Institute for Artificial Intelligence) and adjunct professor of human-computer interaction at the International University in Germany. He has published widely on user-adaptive systems for over 15 years, and he consults for leading German firms on matters of personalization and interface design.

Tutorial III: Programming by Demonstration: Intelligent Interfaces for Teaching New Beahvior to a Machine

Henry Lieberman
Media Lab
Massachusetts Institute of Technology
http://www.media.mit.edu/~lieber/

Programming by Example (also called Programming by Demonstration) is a powerful new technology that lets end-users create programs by recording actions in the user interface rather than by typing statements in a programming language. The user demonstrates a sequence of actions on a concrete example in a graphical user interface, and the system records the actions. Machine Learning and agent technologies are used to generalize programs that can be used in future situations that are analogous to, but not the same as, the situation on which the system was first taught. Programming by Example systems are "macros on steroids".

This tutorial will present this technology, which shows how intelligent user interfaces can dramatically improve the process of software development and make it accessible to users who do not have prior experience with programming. The ideas are, of course, best presented by example. We will survey many systems of this type, including live demonstrations. We will also do in-class design exercises, such as "Wizard of Oz" and "Short-Order Programming" exercises to give attendees hands-on experience with the technology.

Henry Lieberman is the editor of a new book, "Your Wish is my Command", published by Morgan Kauffman, which will serve as text for the tutorial. This book collects 19 articles which describe PBE systems for such diverse applications as text editing, graphical editing, CAD/CAM, animation, games, web browsing, teaching children programming, and others. He also maintains the Programming by Example Web site, at http://www.media.mit.edu/~lieber/PBE/. This site also contains the book, "Watch What I Do", Allen Cypher, ed. the other major reference in this field.

Tutorial IV: Animated Pedagogical Agents

W. Lewis Johnson
Center for Advanced Research in Technology for Education
USC / Information Sciences Institute
http://www.isi.edu/isd/johnson.html

Animated pedagogical agents are emerging as an important way of enhancing the effectiveness of interactive learning environments, and providing intelligent help to other interactive applications. Nonverbal communication is an important part of face-to-face tutorial interaction, and animated pedagogical agents are able to emulate such interactions via a human-computer interface.

Such agents can demonstrate how to perform actions, use locomotion, gaze, and gestures to focus the student's attention, and use gaze to regulate turn-taking in mixed-initiative dialogues. Head nods and facial expressions can provide unobtrusive feedback on the student's utterances and actions without unnecessarily disrupting the student's train of thought. Personified agents can exhibit emotion and personality, enhancing the vividness of the interaction. If such agents are built using suitable autonomous agent architectures, they can support learning adaptively in dynamic environments, and can be extended to multi-user applications such as distributed team training environments.

This tutorial will survey current research in animated pedagogical agent technology, and discuss the results of evaluation studies that have been performed to date. It will examine common methods and techniques for implementing such agents, and discuss how they can be best put to use.

W. Lewis Johnson is director of the Center for Advanced Research in Technology for Education (CARTE) at USC / Information Sciences Institute, which is developing animated pedagogical agents for a variety of learning environments. Dr. Johnson is President of the Artificial Intelligence in Education Society, and past chair of ACM SIGART. He has been active in promoting the development of autonomous agent research as a field, through the establishment of the International Conference on Autonomous Agents and the SIGART Award for Excellence in Autonomous Agent Research.