11-12 July 2009, Pasadena, CA, USA
Paper submission deadline: March 6, 2009**
Both within AI systems and in interactive systems, the ability to explain reasoning processes and results can have substantial impact. Within the field of knowledge-based systems, explanations have been considered as an important link between humans and machines. There, their main purpose has been to increase the confidence of the user in the system’s result (persuasion) or the system as a whole (satisfaction), by providing evidence of how it was derived (transparency). More recently, in recommender systems good explanations have also been used to help to inspire user trust and loyalty (trust), and make it quicker and easier (efficiency) for users to find what they want (effectiveness). Additional AI research has focused on how computer
systems can themselves use explanations, for example to form new generalizations (learning). Explanations have also been used to increase the external user's understanding of a domain (education).
Current interest in mixed-initiative systems provides a new context in which explanation issues may play a crucial role. When knowledge-based systems are partners in an interactive socio-technical process, with incomplete and changing problem descriptions, communication between human and software systems is a central part. Thus explanations exchanged between human agents and software agents may play an important role in mixed-initiative problem solving.
This workshop series aims to draw on multiple perspectives on explanation, to examine how explanation can be applied to further the development of robust and dependable systems, and increase transparency, user sense of control (scrutability), trust, acceptance and decision support.
If you would like to participate in discussions on this topic or like to receive further information about this workshop you might consider
joining the Yahoo!-group.
Information on explanation research is also collected at
http://on-explanation.net.
GOALS AND AUDIENCE
We invite original contributions to the research on explanations from a variety of areas and communities such as computer science, cognitive science, linguistics, philosophy of science, psychology, and education. In addition to presentations and discussions of invited contributions and invited talks, this workshop will offer organised and open sessions for targeted discussions and creating an interdisciplinary community. Demonstration sessions will provide the opportunity to showcase explanation-enabled/-aware applications.
TOPICS OF INTEREST
Suggested topics for contributions (not restricted to IT views):
Models and knowledge representations for explanations
Integrating application and explanation knowledge
Explanation-awareness in (designing) applications
Methodologies for developing explanation-aware systems
Explanations and learning
Context-aware explanation vs. explanation-aware context
Confidence and explanations
Privacy, security, trust, and explanation
Empirical studies of explanations
Requirements and needs for explanations to support human understanding
Explanation of complex, autonomous systems
Co-operative explanation
Visualising explanations
Dialogue management and natural language generation
Submissions on additional topics are welcome as well.
SUBMISSIONS AND STYLE
Workshop submissions will be electronic, in pdf format only, using the EasyChair submission system linked from the workshop website.
Papers must be written in English and not exceed 12 pages in the Springer LNCS format. At least one author of each accepted paper must register for the workshop and present the contribution in order to be published in the workshop proceedings. The organising committee is considering editing a special issue of an appropriate international journal (e.g., Kluwer’s Knowledge-based Systems, Elsevier’s Expert Systems with Applications, or Springer’s
Information System Frontiers) depending on the number and quality of the submissions.
Those wishing to participate providing a live system demonstration should submit a proposal (1-2 pages). Those wishing to participate without paper or demo submission should submit a brief synopsis of their relevant work or at least a brief statement of interest.
Non-archival working notes will be produced containing the papers presented at the workshop.
If you have questions please contact the chairs at
this email address.
IMPORTANT DATES
Submission deadline: March 6, 2009
Notification of acceptance: April 17, 2009
Camera-ready versions of papers: May 8, 2009
IJCAI-09 Workshop Program: July 11-12, 2009
WORKSHOP SCHEDULE
The schedule will be made available on the workshop website. See the workshop website for an agenda overview und links to past workshops.
INVITED TALKS
Talks by two invited speakers, each representing a different community addressing explanation issues, are planned.
CHAIRS
Thomas R. Roth-Berghofer, German Research Center for Artificial Intelligence DFKI GmbH, Germany
thomas.roth-berghofer at dfki de
Nava Tintarev, Department of Computer Science, University Of Aberdeen, UK
n.tintare at abdn ac uk
David B. Leake
Computer Science Department, Indiana University, USA
leake at cs indiana edu
PROGRAMME COMMITTEE
Agnar Aamodt, Norwegian Uni of Science and Technology (NTNU)
David W. Aha, Navy Center for Applied Research in AI, USA
Patrick Brézillon, LIP6, France
Jörg Cassens, NTNU
Francisco Javier Díez, UNED Madrid, Spain
Babak Esfandiari, Carleton University, Canada
Pierre Grenon, IFOMIS, University of Saarbrücken, Germany
Anders Kofod-Petersen, SINTEF, Norway
Hector Muñoz-Avila, Lehigh University, USA
Paulo Pinheiro da Silva, University of Texas, El Paso, USA
Enric Plaza, IIIA-CSIC, Spain
Michael M. Richter, University of Calgary, Canada
Sven Schwarz, DFKI, Germany
Gheorghe Tecuci, George Mason University, Fairfax, VA, USA
Douglas Walton, University of Winnipeg, Canada
