User Models in Dialog Systems

1. Front Matter

   Pages I-XI

   PDF

2. A Survey of User Modeling

   1. Front Matter

      Pages 1-3

      PDF

   2. User Models in Dialog Systems

      • Wolfgang Wahlster, Alfred Kobsa

      Pages 4-34

   3. Stereotypes and User Modeling

      • Elaine Rich

      Pages 35-51

   4. A Taxonomy of Beliefs and Goals for User Models in Dialog Systems

      • Alfred Kobsa

      Pages 52-68

3. Building User Models

   1. Front Matter

      Pages 69-73

      PDF

   2. KNOME: Modeling What the User Knows in UC

      • David N. Chin

      Pages 74-107

   3. Detecting and Responding to Plan-Oriented Misconceptions

      • Alexander Quilici

      Pages 108-132

   4. Plan Recognition and Its Use in Understanding Dialog

      • Sandra Carberry

      Pages 133-162

   5. Learning the User’s Language: A Step Towards Automated Creation of User Models

      • Jill Fain Lehman, Jaime G. Carbonell

      Pages 163-194

4. Exploiting User Models

   1. Front Matter

      Pages 195-199

      PDF

   2. The Use of Explicit User Models in a Generation System for Tailoring Answers to the User’s Level of Expertise

      • Cécile L. Paris

      Pages 200-232

   3. Highlighting a User Model to Respond to Misconceptions

      • Kathleen F. McCoy

      Pages 233-254

   4. But What Will the Listener Think? Belief Ascription and Image Maintenance in Dialog

      • Anthony Jameson

      Pages 255-312

   5. Incorporating User Models into Expert Systems for Educational Diagnosis

      • Robin Cohen, Marlene Jones

      Pages 313-333

5. Shortcomings of Current Models, Prospects for the Future

   1. Front Matter

      Pages 335-340

      PDF

   2. Realism About User Modeling

      • Karen Sparck Jones

      Pages 341-363

   3. User Models and Conversational Settings: Modeling the User’s Wants

      • Katharina Morik

      Pages 364-385

   4. Student Modeling in Intelligent Tutoring Systems — Implications for User Modeling

      • Robert Kass

      Pages 386-410

   5. GUMS — A General User Modeling Shell

      • Timothy W. Finin

      Pages 411-430

User models have recently attracted much research interest in the field of artificial intelligence dialog systems. It has become evident that flexible user-oriented dialog behavior of such systems can be achieved only if the system has access to a model of the user containing assumptions about his/her background knowledge as well as his/her goals and plans in consulting the system. Research in the field of user models investigates how such assumptions can be automatically created, represented and exploited by the system in the course of an "on-line" interaction with the user. The communication medium in this interaction need not necessarily be a natural language, such as English or German. Formal interaction languages are also permit­ ted. The emphasis is placed on systems with natural language input and output, however. A dozen major and several more minor user modeling systems have been de­ signed and implemented in the last decade, mostly in the context of natural-language dialog systems. The goal of UM86, the first international workshop on user model­ ing, was to bring together the researchers working on these projects so that results could be discussed and analyzed, and hopefully general insights be found, that could prove useful for future research. The meeting took place in Maria Laach, a small village some 40 miles south of Bonn, West Germany. 25 prominent researchers were invited to participate.

• artificial intelligence
• behavior
• cognition
• diagnosis
• expert system
• intelligence
• knowledge
• learning
• modeling

• Department of Computer Science, University of Saarbrücken, Saarbrücken 11, Fed. Rep. of Germany

  Alfred Kobsa, Wolfgang Wahlster

Policies and ethics