Advertisement

A Neural Learning Framework for Advisory Dialogue Systems

  • Hans-Günter Lindner
  • Freimut Bodendorf
Conference paper

Abstract

A domain independent neural learning framework for advisory dialogue systems (ADS) is suggested. A connectionist view of user and task modeling is introduced that can be implemented in a neural knowledge network. It implicitly interprets man-computer interaction and causes adaptive task support. Adaptive inference is drawn by modifying the causal connections during interaction. The interpretation of the network gives insights into the user’s knowledge and preferences. Reasons for misconceptions can be estimated and interpreted by users, designers and rules for network modification.

Neural ADS learn empirically in real-time to raise future system performance but can also be programmed by experts. Additionally, the network can be used for predicting the behaviour of the whole system or its parts.

Advantages are constant retrieval time for associated information, extendability, and variability. Implementing the framework does not require special hardware or neural simulators. To demonstrate the applicability, two prototypical spreadsheet applications are introduced.

Keywords

Processing Element Action Atom Bidirectional Associative Memory Connection Matrix Semantic Field 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Bodendorf F, ‘Benutzermodelle — ein konzeptioneller Überblick’, Wirtschaftsinformatik, 34, 2, 1992: 233–245.Google Scholar
  2. [2]
    Bodendorf F, Lindner H-G, and Linß H, ‘Benutzermodellierung mit Hilfe Neuronaler Netze — Ein Prototyp für OS/2-Nutzer’, Wirtschaftsinformatik-Arbeitspapier 4, Nürnberg, 1990.Google Scholar
  3. [3]
    Chang A-M, Whinston A B, and Holsapple C W, ‘The Hyperknowledge Environment of Model Management Systems’, in Stohr E A and Konsynski B R (eds.), ‘Information Systems and Decision Processes’, IEEE Computer Society Press, Los Alamitos et al., 1992: 206-217.Google Scholar
  4. [4]
    Ellis C A, Gibbs S J, ‘Active Objects: Realities and Possibilities’, in Kim W and Lochovsky F H (eds.), ‘Object-Oriented Concepts, Databases, and Applications’, Addison-Wesley, Reading, 1992: 561-572.Google Scholar
  5. [5]
    Kosko B, ‘Neural Network and Fuzzy Systems’, Englewood Cliffs, Prentice Hall, 1992.Google Scholar
  6. [6]
    Lindner H-G, Eggert V and Reinheimer S, ‘Computergestützte Individualisierung von Gruppenprozessen am Beispiel einer Examenskorrektur’, Wirtschaftsinformatik-Arbeitspapier 11, Nürnberg, 1992.Google Scholar
  7. [7]
    Lindner H-G, ‘Konzeption eines Modells zur Entwicklung adaptiver und beratender Anwendungssysteme’, Dissertation, Nürnberg, 1993.Google Scholar
  8. [8]
    Lodewyck R W and Deng P-S, ‘Experimentation with a Back-propagation Neural Network — An Application to Planning End User System Development’, Information & Management, 24, 1993: 1–8.CrossRefGoogle Scholar
  9. [9]
    Myers B, ‘Demonstrational Interfaces: A Step beyond Direct Manipulation’, IEEE Computer, 25, 8, 1992.CrossRefGoogle Scholar
  10. [10]
    Silverman B G, ‘Building a Better Critic: Recent Empirical Results’, IEEE EXPERT, 7, 2, 1992.CrossRefGoogle Scholar
  11. [11]
    Sprague R H Jr. and Hill T R, The Nature of Work, in Stohr E A and Konsynski B R (eds.), ‘Information Systems and Decision Processes’, IEEE Computer Society Press, Los Alamitos et al., 1992: 183–190.Google Scholar

Copyright information

© Springer-Verlag/Wien 1993

Authors and Affiliations

  • Hans-Günter Lindner
    • 1
  • Freimut Bodendorf
    • 1
  1. 1.Wirtschaftsinformatik IIUniversität Erlangen-NürnbergNürnberg 1Germany

Personalised recommendations