JACIII Vol.14 No.6 pp. 741-745
doi: 10.20965/jaciii.2010.p0741


Conversation System with State Information

Elyse Marie Glina and Byeong-Ho Kang

University of Tasmania, Hobart, Tasmania 7001, Australia

February 10, 2010
April 10, 2010
September 20, 2010
conversation systems, multiple classification ripple down rules, knowledge acquisition
Most current approaches to conversation system development invoke a complex set of language parsing rules or development tools difficult for novices to handle and are unable to convincingly simulate advanced natural language features such as topic awareness or conversation thread involvement. This study proposes an alternate approach based on the Ripple Down Rules (RDR) algorithm, presently used to enable more effective maintenance of expert systems. This tree-based algorithm enables a conversation system to travel incrementally deeper into a particular topic, then to switch based on context-dependent information to the correct previously discussed topic – resulting in a highly reusable method of developing conversation systems based around a variety of topics.
Cite this article as:
E. Glina and B. Kang, “Conversation System with State Information,” J. Adv. Comput. Intell. Intell. Inform., Vol.14 No.6, pp. 741-745, 2010.
Data files:
  1. [1] R. Davis, “Knowledge Based Systems,” Science, American Association for the Advancement of Science, New York, Vol.231, No.4741, pp. 957-963, 1986.
  2. [2] E. Feigenbaum and A. Bond (ed.), “Expert systems in the 1980s,” State of the art report on machine intelligence, Pergamon Infotech, New York, 1981.
  3. [3] D. Merritt, “Building Expert Systems In Prolog,” Springer-Verlag, 1989.
  4. [4] P. Compton and R. Jansen, “A philosophical basis for knowledge acquisition,” Knowledge Acquisition, Vol.2, No.3, pp. 241-258, 1990.
  5. [5] T. Cao and P. Compton, “A simulation framework for knowledge acquisition evaluation,” P. of the Twenty-Eighth Australasian Conf. on Computer Science, Vol.38, pp. 353-336, 2005.
  6. [6] P. Compton, L. Peters et al., “Experience with Ripple-Down-Rules,” Knowledge-Based Systems, Vol.19, pp. 356-362, 2006.
  7. [7] G. Edwards, P. Compton et al., “Piers: A pathologist-maintained expert system for the interpretation of chemical pathology reports,” Pathology, Vol.25, No.1, pp. 27-34, 1993.
  8. [8] A.L.I.C.E. AI Foundation, “A.L.I.C.E.,”
    (last accessed 2009).
  9. [9] D. Coniam, “Evaluating the language resources of chatbots for their potential in English as a second language,” ReCALL, Vol.20, No.1, pp. 98-116, 2008.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Jul. 19, 2024