Advertisement

A SOMAgent for Identification of Semantic Classes and Word Disambiguation

  • Vivian F. López
  • Luis Alonso
  • María Moreno
Conference paper
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 55)

Abstract

This work describes a method that uses artificial neural networks, specially a Self- Organising Map (SOM), to determine the correct meaning of a word. By using a distributed architecture, we take advantages of the parallelism in the different levels of the Natural Language Processing system, for modeling a community of conceptually autonomous agents. Every agent has an individual representation of the environment, and they are related through the coordinating effect of communication between agents with partial autonomy. The aim of our linguistic agents is to participate in a society of entities with different skills, and to collaborate in the interpretation of natural language sentences in a prototype of an Automatic German- Spanish Translator.

Keywords

agent natural language processing semantic syntactic automatic translator Kohonen Maps 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Balsa, J., Lopes, G.: A distributed approach for a robust and evolving NLP system. In: Christodoulakis, D.N. (ed.) NLP 2000. LNCS, vol. 1835, pp. 151–161. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  2. 2.
    Christiansen, M., Kirby, S.: Language Evolution. Oxford University Press, Oxford (2003)Google Scholar
  3. 3.
    Elman, J., Bates, A., Johnson, A., KarmiloffSmith, A., Parisi, D., Plunkett, K.: Rethinking innateness: A connectionist perspective on development. MIT Press, Cambridge (1996)Google Scholar
  4. 4.
    Fodor, J.A., Pylyshyn, Z.W.: Connectionism and cognitive architecture: A critical analysis. In: Connections and symbols. MIT Press, Cambridge (1998)Google Scholar
  5. 5.
    Gallant, S.I.: A practical approach for representing context and for performing word sense disambiguation using neural networks. ACM SIGIR Forum 3(3), 293–309 (1991)Google Scholar
  6. 6.
    Gärdenfors, P.: Conceptual Spaces. MIT Press, Cambridge (1999)Google Scholar
  7. 7.
    Hirst, G.: Semantic interpretation and the resolution of ambiguity. Cambridge University Press, Cambridge (1987)Google Scholar
  8. 8.
    Honkela, T.: Self-Organizing maps in natural language processing. Thesis for the degree of Doctor of Philosophy, Helsinki University of Technology, Department of Computer Science and Engineering. Public defense at 12th of December (1997)Google Scholar
  9. 9.
    Honkela, T., Winter, J.: Simulating language learning in community of agents using self-organizing maps. Technical report, Helsinky University of Technology, Computer and Information Science Report A71 (2003) ISBN 951-22-6881-7Google Scholar
  10. 10.
    Honkela, T.: Philosophical aspects of neural, probabilistic and fuzzy modeling of language use and translation. In: International joint conference on neural networks, IJCNN 2007, pp. 2881–2886 (2007)Google Scholar
  11. 11.
    Kaski, S.: Dimensionality reduction by random mapping: Fast similarity computation for clustering. In: Proceedings of IJCNN98, International Joint Conference on Neural Networks, vol. 1, pp. 413–418. IEEE Service Center, Piscataway (1998)Google Scholar
  12. 12.
    Klein, E., et al.: Generalized phrase structure grammar (1985)Google Scholar
  13. 13.
    Charniak, E.: Statistical language learning. MIT Press, Cambridge (1993)Google Scholar
  14. 14.
    Koehn, P., Och, F.J., Marcu, D.: Statistical phrase-based translation. In: NAACL 2003: Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, pp. 48–54. Association for Computational Linguistics, Morristown (2003)CrossRefGoogle Scholar
  15. 15.
    Kohonen, T.: Self-organized formation of topologically correct feature maps. Neurocomputing, 511–522 (1990)Google Scholar
  16. 16.
    Kohonen, T.: Self-organized maps. Proceedings of the IEEE 78(9), 1464–1480 (1990b)CrossRefGoogle Scholar
  17. 17.
    Kohonen, T.: SOM-PAK: The self-Organizing map program package. Helsinki University of Technology Laboratory of Computer and Information Science, Finland (1995)Google Scholar
  18. 18.
    Koskenniemi, K.: Two-level morphology: A general computational model for word-form recognition and production. PhD thesis, University of Helsinki, Department of General Linguistics (1983)Google Scholar
  19. 19.
    Li, P.: Language acquisition in a self-organizing neural network model. In: Quinlan, P. (ed.) Connectionist models of development: Developmental processes in real and artificial neural networks, pp. 115–149. Psychology Press, New York (2003)Google Scholar
  20. 20.
    Li, P.: Farkas Early lexical development in a self-organizing neural network. Neural Networks 17, 1345–1362 (2004)CrossRefGoogle Scholar
  21. 21.
    López, V.: Semantic disambiguation based on conexionist methods for a German Spanish problem of automatic translation. Thesis for the degree of Doctor in computer science. Valladolid University, Spain (1996)Google Scholar
  22. 22.
    MacWhinney, B.: Lexicalist connectionism. In: Broeder, P., Murre, J.M. (eds.) Models of language acquisition: Inductive and deductive approaches, pp. 342–932. Oxford University Press, Oxford (2001)Google Scholar
  23. 23.
    Mayberry III, M.R., Miikkulainen, R.: Lexical disambiguation based on distributed representations of context frequency. In: Proceedings of the 16th Annual Conference of the Cognitive Science Society (1994)Google Scholar
  24. 24.
    Morris, G., Hirst: Semantic interpretation and ambiguity. Artificial Intelligence 34, 131–177 (1998)Google Scholar
  25. 25.
    Pollack, J.B.: Recursive distributed representations. Artificial Intelligence 46, 77–105 (1990)CrossRefGoogle Scholar
  26. 26.
    Pulkki, V.: Data averaging inside categories with the selforganizing map. Report A27, Helsinki University of Technology, Laboratory of Computer and Information Science, Espoo, Finland (1995)Google Scholar
  27. 27.
    Quinlan, P.: Modeling human development: In brief. In: Quinlan, P. (ed.) Connectionist models of development: Developmental processes in real and artificial neural networks, p. 112. Psychology Press, New York (2003)Google Scholar
  28. 28.
    Ritter, H., Kohonen, T.: Self-organizing semantic maps. Biological Cybernetics 61(4), 241–254 (1989)CrossRefGoogle Scholar
  29. 29.
    Ritter, H., Kohonen, T.: Learning “semantotopic maps” from context. In: Proceedings of IJCNN-90-WASH-DC, International Joint Conference on Neural Networks, vol. I, pp. 23–26. Lawrence Erlbaum, Hillsdale (1990)Google Scholar
  30. 30.
    Rumelhart, D., McClelland, J.: On learning the past tenses of English verbs. In: Parallel Distributed Processing. Psychological and Biological Models, vol. 2, pp. 216–271. MIT Press, Cambridge (1986)Google Scholar
  31. 31.
    Scholtes, J.C.: Resolving linguistic ambiguities with a neural data-oriented parsing (DOP) system. In: Aleksander, I., Taylor, J. (eds.) Artificial Neural Networks, vol. 2, II, pp. 1347–1350. North-Holland, Amsterdam (1992)Google Scholar
  32. 32.
    Schütze, H.: Dimensions of meaning. In: Proceedings of Supercomputing, pp. 787–796 (1992)Google Scholar
  33. 33.
    Silva, J.L., Lima, V.: An alternative approach to lexical categorical disambiguation using a multi-agent system architecture. In: Proceedings of the RANLP 1997, Bulgaria, pp. 6–12 (1997)Google Scholar
  34. 34.
    Stefanini, M.H., Berrendonner, A., Lallich, G., Oquendo, F.: Talisman: Un système multi-agents gouverné par des lois linguistiques pour le traitement de la langue naturelle. In: COLING 1992, pp. 490–497 (1992)Google Scholar
  35. 35.
    Strube, V.L., Carneiro, P.R., Filho, I.: Distributing linguistic knowledge in a multi-agent natural language processing system: re-modelling the dictionary. In: Procesamiento del lenguaje natural (23), pp. 104–109 (1998) ISSN 1135-5948Google Scholar
  36. 36.
    Sutcliffe, R., Slater, B.: Word sense disambiguation of text by association methods: a comparative study. In: Proceedings of the SEPLN 1994 (1994)Google Scholar
  37. 37.
    Tikkala, A., et al.: The Production of finnish nouns: a psycholinguistically motivated connectionist model. Connect. Sci. 9(3), 295–314 (1997)CrossRefGoogle Scholar
  38. 38.
    Veronis, J., et al.: Word sense disambiguation with very large neural networks extracted from machine readable. Dictionaries. In: COLING 1990, Helsinki (1990)Google Scholar
  39. 39.
    Wermter, S., Riloff, E., Scheler, G.: Connectionist, statistical and symbolic approaches to learning for natural language. Processing. Springer, New York (1996)Google Scholar
  40. 40.
    Wooldridge, M.: Intelligent Agents. In: Weiss, G. (ed.) Multiagent Systems. MIT Press, Cambridge (1999)Google Scholar
  41. 41.
    Zhang, R., Yamamoto, H., Paul, M., Okuma, H., Yasuda, K., Lepage, Y., Denoual, E., Mochihashi, D., Finch, A., Sumita, E.: The NiCTATR statistical machine translation system for IWSLT 2006. In: Proceedings of the International Workshop on Spoken Language Translation, Kyoto, Japan, pp. 83–90 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Vivian F. López
    • 1
  • Luis Alonso
    • 1
  • María Moreno
    • 1
  1. 1.Departamento Informática y AutomáticaUniversidad de SalamancaSalamancaSpain

Personalised recommendations