Advertisement

WEBSOM Method - Word Categories in Czech Written Documents

  • Roman Mouček
  • Pavel Mautner
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5729)

Abstract

We applied well-known WEBSOM method (based on two layer architecture) to categorization of Czech written documents. Our research was focused on the syntactic and semantic relationship within word categories of word category map (WCM). The document classification system was tested on a subset of 100 documents (manual work was necessary) from the corpus of Czech News Agency documents. The result confirmed that WEBSOM method could be hardly evaluated because humans have problems with natural language semantics and determination of semantic domains from word categories.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
  2. 2.
    Manning, C.D., Raghavan, P., Schütze, H.: Introduction to Information Retrieval. Preliminary draft. Cambridge University Press, Cambridge (2007)Google Scholar
  3. 3.
    Kohonen, T.: Self-Organizing map. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  4. 4.
    Fausset, L.V.: Fundamentals of neural networks. Prentice Hall, Engelwood Cliffs (1994)Google Scholar
  5. 5.
    Kaski, S., Honkela, T., Lagus, K., Kohonen, T.: WEBSOM – Self-Organizing Maps of Document Collections. Neurocomputer, 101–117 (1998)Google Scholar
  6. 6.
    Ritter, H., Kohonen, T.: Self-organizing semantic maps. Biological Cybernetics 61, 241–254 (1989)CrossRefGoogle Scholar
  7. 7.
    Kohonen, T., Hynninen, J., Kangas, J., Laaksonen, J.: SOM-PAK, The self-organizing map program package (1996)Google Scholar
  8. 8.
    Vesanto, J., Himberg, J., Alhoniemi, E., Parhankangas, J.: SOM Toolbox for Matlab (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Roman Mouček
    • 1
  • Pavel Mautner
    • 1
  1. 1.Department of Computer Science and EngineeringUniversity of West BohemiaPilsenCzech Republic

Personalised recommendations