DETECTING, REPAIRING, AND PREVENTING HUMAN--MACHINE MISCOMMUNICATION

AAAI '96 Workshop
Portland, OR
August 4, 1996

The focus of this workshop is to bring together researchers interested in developing theoretical models of robust interaction or in designing robust systems. Topics of interest include, but are not limited to, the following:

• Theories that delineate what knowledge must be represented, how it will be obtained and updated, and how responsibility for achieving robustness might be distributed among the interactants.

• Strategies for identifying potential causes of breakdowns, such as ambiguities, misconceptions, and plan misrecognition, in order to avert miscommunication.

• Strategies for identifying symptoms of actual breakdowns, such as deviations from expected behavior, unresolvable ambiguities, and speech errors.

• Techniques for correcting errors in interpretation that have been used in other areas of AI, such as plan recognition and computer vision, and in related areas, such as human-computer interaction and multimedia.

• Approaches to minimizing and correcting miscommunication in tutoring systems and education.

• Empirical data regarding the occurrence of miscommunication and approaches to robust communication that derive from empirical methods.

• Research in knowledge representation that would be useful in detecting, repairing, and preventing miscommunication.

Workshop Program

8:30am Opening remarks
Session 1: Empirical data regarding the occurence of miscommunication
8:45am "Toward error resolution for next-generation human language technology and multimodal systems" Oviatt
9:15am Prevention and repair of breakdowns in a simple task domain Hansen, Novick, and Sutton
9:45am Refining the categories of miscommunication Jordan and Thomason

Break

11:00am Pragmatic issues in handling miscommunication: Observations of a spoken natural language dialog system Smith and Gordon

Session 2: Strategies for identifying potential causes of breakdowns
11:30am Reducing miscommunication in spoken human-machine dialogue (Page 1) page 2 page 3 page 4 page 5 pages 6-8 Dybkjaer, Bernsen, and Dybkjaer
12:00pm Miscommunication in multi-modal collaboration Traum and Dillenbourg

12:30--2:00pm LUNCH

Session 3: KR and Reasoning about miscommunication
2:00pm Conversational adequacy: Mistakes are the essence Perlis and Purang
2:30pm An integrated approach to evaluating text coherence and its application to the prevention of reader misconceptions Donaldson, Makuta, and Cohen
3:00pm Tradeoffs in modelling participants' expectations about a dialogue McRoy

3:30pm Break

Session 4: Repair in spoken language systems
4:00pm DISCO: A four-step dialogue recovery program LuperFoy and Duff
4:30pm A genetic programming approach to robust interactive dialogue interpretation Carolyn Rose
5:00pm On the use of expectations for detecting and repairing human-machine miscommunication Danieli

5:30pm Closing discussion

Position papers
Campbell
Fass
Nerzic
O'leary

The complete workshop announcement

Susan McRoy, Program Chair