TALISMAN: A multi-agent system for natural language processing

  • Marie-Hélène Stefanini
  • Yves Demazeau
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 991)


Natural Language Processing raises the problem of ambiguities and therefore the multiple solutions resulting from them. Architectures based on sequential levels, in which each module corresponds to a linguistic level (preprocessing, morphology, syntax, semantics) have shown their limitations. A sequential architecture does not allow a real exchange between different modules. This leads to the unavailability of the linguistic information needed for the reduction of ambiguities. Due to the necessity for cooperation between different modules we consider the use of a new architecture which stems from the techniques in Distributed Artificial Intelligence. This paper presents a general Natural Language Processing system called TALISMAN. One of the originalities of this system is the distributed treatment of sentence analysis (as opposed to a classic sequential treatment) and the introduction of linguistic laws which handle the communication between agents, without central control. At the implementation level, the system brings openness to dictionary modification, grammars and strategies of analysis, as well as the necessary mechanisms for the integration of new modules.


Natural language processing the understanding of written French distributed artificial intelligence multi-agent systems law governed systems communication protocols 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [Ant 88]
    G. Antoniadis, G. Lallich-Boidin, Y. Polity & J. Rouault, “A french linguistic model for an information retrieval system”. ACM SIGIR, Grenoble, June 1988.Google Scholar
  2. [Berr 90]
    A. Berrendonner, “Grammaire pour un analyseur: aspects morphologiques”, Les Cahiers du CRISS, N∘ 15, November 1990.Google Scholar
  3. [Ben 88]
    P. Benoit, Ph. Rincel, P. sabatier, D. Vienne: “A User-Friendly Natural Language Interface to Oracle”, Proceedings of the European Oracle Users' group Conference, Paris 1988.Google Scholar
  4. [Bert 92]
    S. Berthet, Y. Demazeau, O. Boissier., “Knowing Each Other Better.” in 11th International Workshop on DAI, An Arbor, Michigan, February 1992.Google Scholar
  5. [Bin 89]
    J. L. Binot et al.,A Multi-Mode Interface for Man-Machine Interaction. “Literature review and general architecture”. Esprit P2474, Deliverable d1. Bruxelles, 1989.Google Scholar
  6. [Bon 88]
    A.H. Bond & L. Gasser, “Readings in Distributed Artificial Intelligence”. Morgan Kaufmann, 1988.Google Scholar
  7. [Dem 90]
    Y. Demazeau & J.P. Mueller, eds (+ Introduction) “Decentralized A.I.”. Demazeau & Muller eds., North-Holland, Elsevier, 1990.Google Scholar
  8. [Dem 92]
    Y. Demazeau & J.P. Mueller, eds (+ Introduction) “Decentralized Artificial Intelligence II”. Demazeau & Muller eds., North-Holland, Elsevier, 1992.Google Scholar
  9. [Dem 95]
    Y. Demazeau “From Cognitive Interactions to Collective Behaviour in Agent-Based Systems”. European Conference on Cognitive Science, Saint Malo, Avril 1995.Google Scholar
  10. [Erl 87]
    Erli, SAPHIR, Manuel de description du logiciel, Société Erli 1987.Google Scholar
  11. [Erm 80]
    L. D. Erman, F. Hayes-Roth, R. Lesser, D.R. Reddy, “The Hearsay-II speech understanding system: integrating knowledge to resolve uncertainty”. ACM Computing Surveys 12, 1980.Google Scholar
  12. [Kui 91]
    E. Kuijpers, G. Lallich-Boidin & J. Rouault,“French System: From a Syntactic Structure to a CMR Expression”. ESPRIT P2474 MMI2 Deliverable d20 for st.3.3.2. Grenoble, CRISS, April 1991.Google Scholar
  13. [Mek 91]
    A. Mekaouche, J.C. Bassano,“Analyseur linguistique multi-expert pour la recherche documentaire”. Avignon, Mai 1991.Google Scholar
  14. [Min 91]
    N.H. Minsky, “The imposition of protocols over open distributed systems”. IEEE Transactions on Software Engineering February 1991.Google Scholar
  15. [New 72]
    A. Newell & H.E. Simon, “Human problem solving”. Englewood Cliffs, 1972.Google Scholar
  16. [Bin 88]
    J. L. Binot, B. Demoen, K. Hanne, L. Solomon, Y. Vasiliou, W. von Hahn, T. Wachtel: “LOQUI: A logic oriented approach to data and knowledge bases supporting natural language interaction”, Proceedings of ESPRIT 88 Conference, North-Holland, 1988.Google Scholar
  17. [Bin 89]
    J. L. Binot et al., A Multi-Mode Interface for Man-Machine Interaction “Literature review and general architecture” Esprit P2474, Deliverable d1, Bruxelles, 1989.Google Scholar
  18. [Kon 95]
    J.L. Koning, M.H.Stéfanini, Y. Demazeau, “DAI Interaction Protocols as Control Strategies in a Natural Language processing System”, IEEE International Conference on Systems, Man and Cybernetics, October, Vancouver.Google Scholar
  19. [Ple 92]
    “Vers une Taxinomie du vocabulaire pour les Systèmes Multi-Agents”, lère journée Nationale du PRC-1A sur les Systèmes Multi-Agents, PRC-IA, Nancy 1992.Google Scholar
  20. [Pei 85]
    F. Pereira, “The TEAM Natural-Language Interface System”, Final Report, SRI International, Menlo Park, 1985.Google Scholar
  21. [Sab 90]
    G. Sabah, “Caramel: A Computational Model of Natural Language Understanding using Parallel implementation”. Proceedings of 9th European Conference on Artificial Intelligence, Stockholm, August 90.Google Scholar
  22. [Sag 91]
    I.A. Sag, “Linguistic theory and natural language processing”. Basic Research Series. E. Klein & F. Veltman (Eds). Symposium Proceedings “Natural language and speech”. Bruxelles, November 1991.Google Scholar
  23. [Sia 91]
    S. Sian, “Adaptation based on Cooperative Learning in Multi-agent Systems”, in Decentralized A.I. 2, Demazeau & Müller, eds., North Holland Elsevier, Amsterdam 1991.Google Scholar
  24. [Ste 93]
    M.H. Stéfanini “TALISMAN: un système multi-agent pour l'analyse du français écrit”, Thèse de Doctorat, Jan. 1993.Google Scholar
  25. [Zwe 89]
    P. Zweigenbaum,“Hélène: Compréhension de compte-rendus d'hospitalisation”. Deuxième Ecole d'été sur le Traitement des Langues Naturelles. L'ENSSAT, Lannion, Juillet 1989.Google Scholar
  26. [Tho 85]
    B. Thomson, F. Thompson: “ASK is Transportable in Half a Dozen Ways”. ACM Transactions on Office Information Systems, Vol 3, N∘ 2, April 1985.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Marie-Hélène Stefanini
    • 1
  • Yves Demazeau
    • 2
  1. 1.Cristal-GresecUniversité StendhalGrenoble Cedex 9France
  2. 2.LIFIA / IMAG / CNRSGrenoble CedexFrance

Personalised recommendations