Kaiserslautern, Germany, February 4, 2005 -- The paper submission deadline for the Fall Symposium on Explanation-aware Computing (ExaCt 2005) is May 6, 2005. The conference will be held in Washington, DC November 3-6, 2005.

OBJECTIVES

With the introduction of intelligent, adaptive systems and decision automation, the need arises for explaining system answers to the user with respect to the application's knowledge. Explanations improve the knowledge of the user in a goal directed way and contribute not only to a higher acceptance but also to better reactions of the user.

In expert systems research, considerable results were produced, but research activity decreased together with the general decline of expert systems research in the nineties of the last century. The major problems with respect to classical expert systems seemed to be solved. Research on explanation is of interest today because the whole scenario of=20 research on knowledge-based systems has changed: knowledge-based systems are no longer considered as boxes that provide a full solution to a problem. Problem solving is seen as an interactive process, a socio-technical process. Problem descriptions can be incomplete and changing. As a consequence, there has to be communication between human and software systems. Communication requires mutual understanding that can be essentially supported by explanations. Such explanations can improve the problem solving process to a large degree.

A major role in interactive systems is played by knowledge management that also is intended to increase the knowledge of the user. Therefore, explanations should be integrated in knowledge management activities and, in particular, related to ontologies.

Procedural programs play an essential role in many stand alone as well as in interactive computer systems. Many such systems are optimization programs dealing with subjective goals of different participants. This asks for explaining procedural programs as well.

An important issue is the acceptance of the results of the systems which is closely related to the trust in its results. Belief in a system can be increased not only by the quality of its output but, more importantly, by evidence of how (and why) it was derived. This adds a psychological component to the scenario, and one can also rely on results obtained in philosophy.

In order to fulfill these aspects, advanced models, methods, and tools are needed that provide mechanisms and techniques for structured management of explanation relevant information, effective ways for retrieving it, and the possibility to integrate explanation and application knowledge. Beyond technical aspects, it becomes important to understand explanations from social and philosophical perspectives on software systems.

GOALS AND AUDIENCE

The major goal of this symposium is to bring researchers, scientists from both industry and academia, and representatives from such different communities and fields as informatics, philosophy, and sociology, together to study, understand, and explore the aspect of explanation in software systems. Besides contributions and invited talks, this symposium will offer organized and open spaces for targeted discussions and creating an interdisciplinary community. As a result, a common understanding on the topic of explanation-aware computing shall originate.

TOPICS OF INTEREST

Topics for contributions include but are not limited to:
   * Models for explanations
   * Methodologies for developing explanation modules
   * Explanation awareness in applications
   * Integrating application and explanation knowledge
   * Methodologies for explanation-embedded development
   * Learning to explain
   * Context-aware explanation
   * Confidence/acceptance and explanations
   * Explanation and human computer interfaces
   * Dialogs and explanation (explanation strategies)
   * Role of explanation in mixed-initiative interaction
   * Requirements and human needs for understanding
   * Perception of complex, autonomous systems
   * Impact of explanation on user satisfaction /solution quality
   * Explanation versus proof
   * Application scenarios
   * Role of explanations in knowledge management
   * Explanation for informal, uncertain, and subjective issues
   * Explanations for changing and incomplete requirements
   * Explanation and case-based reasoning
   * Explanation and agile programming

SUBMISSIONS

Those interested in participating should send a three-page extended abstract describing their related work and areas of interest. Submissions may discuss work in any stage of development, from concepts and future directions to finished work. PDF submissions in AAAI format should be sent to trb at dfki.uni-kl.de. Admission to the symposium is decided upon at least two reviews of the abstracts. A limited number of participants will be invited to prepare long presentations or posters to start up discussion rounds on focused explanation-aware computing topics.

IMPORTANT DATES

   Submission deadline:                     May 6th, 2005
   Notification of acceptance and
   invitation for full papers:              May 31st, 2005
   Camera-ready versions of full papers:    August 31st, 2005=A0

SYMPOSIUM SCHEDULE

The schedule will be made available on the workshop's website.

INVITED TALK

David B. Leake (Indiana University)

SYMPOSIUM CHAIRS

  Thomas R. Roth-Berghofer, trb at dfki.uni-kl.de
  DFKI GmbH / TU Kaiserslautern, Germany

  Stefan Schulz, schulz at sce.carleton.ca
  Systems and Computer Engineering, Carleton University, Canada

  Andrea Woody, awoody at u.washington.edu
  Department of Philosophy, University of Washington, Seattle, USA

PROGRAM COMMITTEE

  Agnar Aamodt, Norwegian University of Science and Technology (NTNU)
  Derek Bridge, University College Cork, Ireland
  Gregor B=FCchel, University of Applied Sciences, K=F6ln, Germany
  Hans-Dieter Burkhard, Humboldt University Berlin, Germany
  J=F6rg Cassens, Norwegian University of Science and Technology (NTNU)
  P=E1draig Cunningham, Trinity College Dublin, Ireland
  Babak Esfandiari, Carleton University, Canada
  Luciano Floridi, Faculty of Philosophy, University of Oxford, UK
  Peter Funk, M=E4lardalen University, Sweden
  Mehmet G=F6ker, Price Waterhouse Coopers, USA
  Pierre Grenon, IFOMIS, University of Saarbr=FCcken, Germany
  Mohamed Khedr, Arab Academy for Science and Technology, Egypt
  Bertin Klein, DFKI GmbH, Kaiserslautern, Germany
  David B. Leake, Indiana University, USA
  David McSherry, University of Ulster, Northern Ireland
  Enric Plaza, IIIA-CSIC, Spain
  Michael M. Richter, University of Kaiserslautern, Germany
  Christophe Roche, University of Savoie, France

Dr. Thomas Roth-Berghofer - Senior Researcher
AG Wissensbasierte Systeme (Knowledge Based Systems Group)
Technische Universit=E4t Kaiserslautern
Knowledge Management Department
German Research Center for Artificial Intelligence DFKI GmbH
Erwin-Schr=F6dinger-Stra=DFe 57, 67663 Kaiserslautern, Germany
Phone:  +49.631.205-4820
mailto:Thomas.Roth-Berghofer@dfki.de
or Thomas@Roth-Berghofer.de
http://www.dfki.uni-kl.de/~roth/