A Hybrid Model for Learning Word-Meaning Mappings

  • Federico Divina
  • Paul Vogt
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4211)


In this paper we introduce a model for the simulation of language evolution, which is incorporated in the New Ties project. The New Ties project aims at evolving a cultural society by integrating evolutionary, individual and social learning in large scale multi-agent simulations. The model presented here introduces a novel implementation of language games, which allows agents to communicate in a more natural way than with most other existing implementations of language games. In particular, we propose a hybrid mechanism that combines cross-situational learning techniques with more informed feedback mechanisms. In our study we focus our attention on dealing with referential indeterminacy after joint attention has been established and on whether the current model can deal with larger populations than previous studies involving cross-situational learning. Simulations show that the proposed model can indeed lead to coherent languages in a quasi realistic world environment with larger populations.


Hybrid Model Joint Attention Perceptual Feature Language Game Association Score 
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.
    Quine, W.V.O.: Word and object. Cambridge University Press, Cambridge (1960)zbMATHGoogle Scholar
  2. 2.
    Bloom, P.: How Children Learn the Meanings of Words. The MIT Press, Cambridge (2000)Google Scholar
  3. 3.
    Tomasello, M.: The cultural origins of human cognition. Harvard University Press (1999)Google Scholar
  4. 4.
    Macnamara, J.: Names for things: a study of human learning. MIT Press, Cambridge (1982)Google Scholar
  5. 5.
    Clark, E.: The principle of contrast: A constraint on language acquisition. In: MacWhinney, B. (ed.) Mechanisms of language acquisition, pp. 1–33. Lawrence Erlbaum Assoc., Hillsdale (1987)Google Scholar
  6. 6.
    Akhtar, N., Montague, L.: Early lexical acquisition: the role of cross-situational learning. First Language, 347–358 (1999)Google Scholar
  7. 7.
    Houston-Price, C., Plunkett, K., Harris, P.: ‘word-learning wizardry’ at 1;6. Journal of Child Language 32, 175–190 (2005)CrossRefGoogle Scholar
  8. 8.
    Smith, A.D.M.: Intelligent meaning creation in a clumpy world helps communication. Artificial Life 9(2), 559–574 (2003)CrossRefGoogle Scholar
  9. 9.
    Vogt, P., Coumans, H.: Investigating social interaction strategies for bootstrapping lexicon development. Journal of Artificial Societies and Social Simulation 6 (2003)Google Scholar
  10. 10.
    Siskind, J.M.: A computational study of cross-situational techniques for learning word-to-meaning mappings. Cognition 61, 39–91 (1996)CrossRefGoogle Scholar
  11. 11.
    Smith, K., Smith, A., Blythe, R., Vogt, P.: Cross-situational learning: a mathematical approach. In: Vogt, P., Sugita, Y., Tuci, E., Nehaniv, C. (eds.) Proceedings of the Emergence and Evolution of Linguistic Communication (EELCIII). Springer, Heidelberg (2006)Google Scholar
  12. 12.
    Baronchelli, A., Loreto, V., Dall’Asta, L., Barrat, A.: Bootstrapping communication in language games: Strategy, topology and all that. In: Cangelosi, A., Smith, A., Smith, K. (eds.) The evolution of language; Proceedings of Evolang 6. World Scientific, Singapore (2006)Google Scholar
  13. 13.
    De Beule, J., De Vylder, B., Belpaeme, T.: A cross-situational learning algorithm for damping homonymy in the guessing game. In: ALIFE X. Tenth International Conference on the Simulation and Synthesis of Living Systems (to appear 2006)Google Scholar
  14. 14.
    Gilbert, N., den Besten, M., Bontovics, A., Craenen, B.G., Divina, F., Eiben, A., et al.: Emerging artificial societies through learning. Journal of Artificial Societies and Social Simulation 9 (2006)Google Scholar
  15. 15.
    Divina, F., Vogt, P.: Modelling language evolution in a complex ecological environment. ILK Research Group Technical Report Series no. 06-01 (2006)Google Scholar
  16. 16.
    Epstein, J.M., Axtell, R.: Growing artificial societies: social science from the bottom up. MIT Press, Cambridge (1996)Google Scholar
  17. 17.
    Steels, L.: The synthetic modeling of language origins. Evolution of Communication 1(1), 1–34 (1997)CrossRefGoogle Scholar
  18. 18.
    Vogt, P.: The emergence of compositional structures in perceptually grounded language games. Artificial Intelligence 167, 206–242 (2005)CrossRefGoogle Scholar
  19. 19.
    Vogt, P.: Lexicon Grounding on Mobile Robots. PhD thesis, Vrije Universiteit Brussel (2000)Google Scholar
  20. 20.
    Steels, L., Kaplan, F.: Situated grounded word semantics. In: Proceedings of IJCAI 1999. Morgan Kaufmann, San Francisco (1999)Google Scholar
  21. 21.
    Vogt, P., Divina, F.: Language evolution in large populations of autonomous agents: issues in scaling. In: Proceedings of AISB 2005: Socially inspired computing joint symposium, pp. 80–87 (2005)Google Scholar
  22. 22.
    Divina, F., Vogt, P.: Perceptually grounded lexicon formation using inconsistent knowledge. In: Capcarrère, M.S., Freitas, A.A., Bentley, P.J., Johnson, C.G., Timmis, J. (eds.) ECAL 2005. LNCS (LNAI), vol. 3630, pp. 644–654. Springer, Heidelberg (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Federico Divina
    • 1
  • Paul Vogt
    • 1
    • 2
  1. 1.Induction of Linguistic Knowledge / Language and Information ScienceTilburg UniversityTilburgThe Netherlands
  2. 2.Language Evolution and Computation Research Unit, School of Philosophy, Psychology and Language SciencesUniversity of EdinburghUK

Personalised recommendations