Skip to main content
SpringerLink
Log in

Connectionist Analysis and Creation of Context for Natural Language Understanding and Knowledge Management

  • Conference paper
  • First Online:
Modeling and Using Context (CONTEXT 1999)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 1688))

  • 524 Accesses

Abstract

Context affects many aspects of the behavior. Natural language understanding is one of the prime examples. This paper summarizes how an artificial neural network, the self-organizing map, can be used in modeling contextuality in data analysis and natural language processing. Important aspects are adaptivity gained by using a learning system, autonomous nature of the processing based on unsupervised learning paradigm, and gradedness of the representation. Examples in the application areas of information retrieval and knowledge management are considered. For instance, the visualization of self-organizing maps provides meaningful context for documents.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Honkela, T., Pulkki, V. and Kohonen, T. (1995). Contextual relations of words in Grimm tales analyzed by self-organizing map. Proceedings of ICANN-95, International Conference on Artificial Neural Networks, F. Fogelman-Soulié and P. Gallinari (eds), vol. 2, EC2 et Cie, Paris, pp. 3–7.

    Google Scholar 

  2. Honkela, T., Kaski, S., Lagus, K., and Kohonen, T. (1996). Newsgroup exploration with WEBSOM method and browsing interface. Technical Report A32, Helsinki University of Technology, Lab. of Computer and Information Science, Espoo, Finland.

    Google Scholar 

  3. Honkela, T. (1998). Kohonen’s Self-Organizing Maps in Intelligent Systems Development. Proceedings of FODO’98, The 5th International Conference on Foundations of Data Organization, Kobe, Japan, pp. 13–19.

    Google Scholar 

  4. Hörmann, H. (1986). Meaning and Context. Plenum Press, New York.

    Google Scholar 

  5. Kaski, S., Honkela, T., Lagus, K., and Kohonen, T. (1996). Creating an order in digital libraries with self-organizing maps. In Proceedings of WCNN-96, World Congress on Neural Networks.

    Google Scholar 

  6. Kaski, S. (1997b). Data exploration using self-organizing maps. Acta Polytechnica Scandinavica, Mathematics, Computing and Management in Engineering Series No. 82. DTech Thesis, Helsinki University of Technology, Finland.

    Google Scholar 

  7. Kaski, S., Honkela, T., Lagus, K., and Kohonen, T. (1998). WEBSOM-self-organizing maps of document collections, Neurocomputing, vol. 21, pp. 101–117.

    Article  MATH  Google Scholar 

  8. Kaski, S., Kangas, J., and Kohonen, T. (1998). Bibliography of Self-Organizing Map (SOM) Papers: 1981—1997. Neural Computing Surveys, 1: 102–350. Available also at http://www.icsi.berkeley.edu/~jagota/NCS/

    Google Scholar 

  9. Kohonen, T. (1982). Self-organizing formation of topologically correct feature maps. Biological Cybernetics, 43(1):59–69.

    Article  MATH  MathSciNet  Google Scholar 

  10. Kohonen, T. (1995). Self-Organizing Maps. Springer, Berlin, Heidelberg.

    Google Scholar 

  11. Kohonen, T., Kaski, S., Lagus, K., and Honkela, T. (1996b). Very large two-level SOM for the browsing of newsgroups. In von der Malsburg, von Seelen, Vorbrüggen, and Sendhoff, editors, Proceedings of ICANN96, International Conference on Artificial Neural Networks, Bochum, Germany, July 16-19, 1996, Lecture Notes in Computer Science, vol. 1112, pp. 269–274. Springer, Berlin.

    Google Scholar 

  12. Lagus, K., Honkela, T., Kaski, S., and Kohonen, T. (1996). Self-organizing maps of document collections: A new approach to interactive exploration. In Simoudis, E., Han, J., and Fayyad, U., editors, Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, pp. 238–243. AAAI Press, Menlo Park, California.

    Google Scholar 

  13. Lin, X., Soergel, D., and Marchionini, G. (1991). A self-organizing semantic map for information retrieval. In Proceedings of 14th. Ann. International ACM/SIGIR Conference on Research & Development in Information Retrieval, pp. 262–269.

    Google Scholar 

  14. Pulkki, V. (1995). Data averaging inside categories with the self-organizing map. Report A27, Helsinki University of Technology, Laboratory of Computer and Information Science, Espoo, Finland.

    Google Scholar 

  15. Ritter, H. and Kohonen, T. (1989). Self-organizing semantic maps. Biological Cybernetics, 61(4):241–254.

    Article  Google Scholar 

  16. Scholtes, J. C. (1992b). Resolving linguistic ambiguities with a neural data-oriented parsing (DOP) system. In Aleksander, I. and Taylor, J., editors, Artificial Neural Networks, 2, volume II, pp. 1347–1350, North-Holland, Amsterdam, Netherlands.

    Google Scholar 

  17. Schütze, H. (1992). Dimensions of meaning. In Proceedings of Supercomputing, pp. 787–796.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Media Lab, University of Art and Design Helsinki, Hämeentie 135 C, FIN-00560, Helsinki, Finland

    Timo Honkela

Authors
  1. Timo Honkela
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. University of Trento, DISA, 5, via Inama, I-38050, Trento, Italy

    Paolo Bouquet  & Massimo Benerecetti  & 

  2. IRST-ITC, Pante di Povo, I-38050, Trento, Italy

    Luciano Serafini

  3. University Paris VI, LIP6 4, Place Jussieu, F-75252, Paris Cedex 05, France

    Patrick Brézillon

  4. University of Trento, 26, via Verdi, I-38050, Trento, Italy

    Francesca Castellani

Rights and permissions

Reprints and permissions

Copyright information

© 1999 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Honkela, T. (1999). Connectionist Analysis and Creation of Context for Natural Language Understanding and Knowledge Management. In: Bouquet, P., Benerecetti, M., Serafini, L., Brézillon, P., Castellani, F. (eds) Modeling and Using Context. CONTEXT 1999. Lecture Notes in Computer Science(), vol 1688. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48315-2_43

Download citation

  • DOI: https://doi.org/10.1007/3-540-48315-2_43

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-66432-1

  • Online ISBN: 978-3-540-48315-1

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation