Conducting the Disambiguation Dialogues between Software Agent Sellers and Human Buyers

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2413)


In the buying and selling interaction in e-commerce, one of the important dialogues is the discourse of resolving the ambiguities. That is to say that both selling and buying agents may have to conduct disambiguating dialogues to some extent in order to resolve the ambiguities and infer the true intents of the other agents. In the paper, we assume buyers are human agents while sellers are software agents and thus the seller agents will construct dialogues to resolve the ambiguities from the buyer agents. To resolve ambiguities, agents rely on four levels of domain knowledge: the world model, the mental model, the language model, and the rational model. In addition, four kinds of disambiguation strategies for the seller agent are implemented: (1) Guessing (2) Filtering (3) Recommending and (4) Asking more hints. Experiments are conducted also to measure the performance of the dialogue system against different parameter settings of the disambiguation strategies. We find that by optimal parameter setting and suitable strategy combination, the seller will result in a shorter dialogue without sacrificing much the optimal profit.


Software Agent Domain Ontology Dialogue System Buyer Agent Interaction History 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lascarides, A., Copestake, A., Brisoe, E.J., Ambiguity and Coherence, Journal of Semantic, 1996, pp 41–65, Oxford University Press.Google Scholar
  2. 2.
    Asher, N., Lascarides, A., Lexical Disambiguation in a Discourse Context, Journal of Semantics, 1995, pp 69–108, Oxford University Press.Google Scholar
  3. 3.
    Nodine, M. H., Unruh, A., Constructing Robust Conversation Policies in Dynamic Agent Communities, Issues in Agent Communication, 2000, pp205–219.Google Scholar
  4. 4.
    Pitt, J., Mamdani, A., Communication Protocols in Multi-agent Systems: A Development Method and Reference Architecture. Issues in Agent Communication, 2000, pp 160–177.Google Scholar
  5. 5.
    Pitt, J., An Operational Semantics for Intentional Specifications of Agent Behaviour in Communication Protocols, ALCP Workshop, London, 2000.Google Scholar
  6. 6.
    Barbuceanu, M., Fox, M. S., COOL, A Language for Describing Coordination in Multi-Agent Systems, in V. Lesser (ed), Proceedings of the First Intl. Conference on Multi-Agent Systems, June 1995, pp 17–25, AAA Press/The MIT Press.Google Scholar
  7. 7.
    Allen, J.F., Miller, B., Ringger, E. and Sikorski, T., A Robust System for Natural Spoken Dialogue, Proc. 34th Meeting of the Assoc. for Computational Linguistics, 1996.Google Scholar
  8. 8.
    Walker, M. A., Limited attention and discourse structure, Computational Linguistics, 22–2, 1996.Google Scholar
  9. 9.
    Maes P., Guttman R., and Moukas A., Agents that Buy and Sell: Transforming Commerce as We Know It. Communications of the ACM 42, 3, 1999, pp. 81.CrossRefGoogle Scholar
  10. 10.
    Greaves M., Heather Holmback, Jeffrey Bradshaw, What Is a Conversation Policy?, Issues in Agent Communication, 2000, pp 118–131.Google Scholar
  11. 11.
    Straach, J., Truemper, K., Learning to Ask Relevant Questions. Artificial Intelligence 111(1–2), 1999, pp 301–327.zbMATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Asher, N. and Lascarides, A. Questions in Dialogue, Linguistics and Philosophy, 1998, pp 237–309, Kluwer Academic Publishers.Google Scholar
  13. 13.
    Bellifemine, F., Poggi, A. and Rimassa, G. JADE-A FIPA-compliant agent framework, in Proceedings of PAAM’99, London, April 1999, pp 97–108.Google Scholar
  14. 14.
    Cohen, P. R. and Levesque, H. J. Communicative Actions for Artificial Agents, in Proceedings of the First International Conference on Multi-agent Systems, 1995 pp 65–72, AAAI Press.Google Scholar
  15. 15.
    Finin, T., Fritzson, R., McKay, D. and McEntire, R., KQML as an agent communication language, in f Proceedings of the 3rd International Conference on Information and Knowledge Management (CIKM), 1994, ACM Press.Google Scholar
  16. 16.
  17. 17.
    Searle, J. R., Speech Acts, 1969, Harvard University Press.Google Scholar
  18. 18.
    Wu, S. H. and Soo, V. W., Game Theoretic Approach to Multi-Agent Coordination by Negotiation with a Trusted Third Party, In Proceeding of the Third International Conference on Autonomous Agents, 1999.Google Scholar
  19. 19.
    FIPA Interaction Protocol Library Specification.
  20. 20.
    FIPA Agent Communication Language Specification.
  21. 21.
    Hovy, E. H., Automated discourse generation using discourse structure relations, Artificial Intelligence, 63, 1993, pp 341–385.CrossRefGoogle Scholar
  22. 22.
    Wilks, Y., Stevenson, M., Word Sense Disambiguation using Optimized Combinations of Knowledge Sources, In Proceedings of COLING-ACL’98, Montreal, Canada, 1998.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  1. 1.Department of Computer ScienceNational Tsing Hua UniversityHsinchu cityTaiwan

Personalised recommendations