Advertisement

Self Organizing Maps in NLP: Exploration of Coreference Feature Space

  • Andre Burkovski
  • Wiltrud Kessler
  • Gunther Heidemann
  • Hamidreza Kobdani
  • Hinrich Schütze
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6731)

Abstract

In Natural Language Processing, large annotated data sets are needed to train language models using supervised machine learning methods. To obtain such labeled data sets, time consuming manual annotation is required. To facilitate this process, we propose a SOM-based approach: The SOM sorts the data through unsupervised training, mapping the space of linguistic features to a 2D-grid. The grid visualization is used for efficient interactive labeling of the data clusters. In addition, the interactive SOM visualization allows computational linguists to explore the topology of the feature space and design new features.

Keywords

self organizing maps coreference resolution annotation visualization natural language processing feature engineering 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kohonen, T.: The Self-Organizing Map. Proceedings of the IEEE 78(9), 1464–1480 (1990)CrossRefGoogle Scholar
  2. 2.
    Kaski, S., Honkela, T., Lagus, K., Kohonen, T.: WEBSOM - Self-Organizing Maps of Document Collections. Neurocomputing 21, 101–117 (1997)CrossRefMATHGoogle Scholar
  3. 3.
    Li, P., Farkas, I., MacWhinney, B.: Early lexical development in a self-organizing neural network. Neural Networks 17(8-9), 1345–1362 (2004)CrossRefGoogle Scholar
  4. 4.
    Heidemann, G., Saalbach, A., Ritter, H.: Semi-Automatic Acquisition and Labelling of Image Data Using SOMs. In: European Symposium on Artificial Neural Networks, pp. 503–508 (2003)Google Scholar
  5. 5.
    Moehrmann, J., Bernstein, S., Schlegel, T., Werner, G., Heidemann, G.: Optimizing the Usability of Interfaces for the Interactive Semi-Automatic Labeling of Large Image Data Sets. In: HCI International, Springer, Heidelberg (to appear, 2011)Google Scholar
  6. 6.
    Pradhan, S.S., Hovy, E., Marcus, M., Palmer, M., Ramshaw, L., Weischedel, R.: OntoNotes: A Unified Relational Semantic Representation. In: International Conference on Semantic Computing, pp. 517–526 (2007)Google Scholar
  7. 7.
    Elango, P.: Coreference Resolution: A Survey. In: Technical Report, University of Wisconsin Madison (2005)Google Scholar
  8. 8.
    Clark, J., Gonzàles-Brenes, J.: Coreference: Current Trends and Future Directions. In: Technical Report, Language and Statistics II Literature Review (2008)Google Scholar
  9. 9.
    Kobdani, H., Schütze, H., Burkovski, A., Kessler, W., Heidemann, G.: Relational feature engineering of natural language processing. In: Proceedings Association for Computational Linguistics International Conference on Information and Knowledge Management, pp. 1705–1708 (2010)Google Scholar
  10. 10.
    Ng, V., Cardie, C.: Improving Machine Learning Approaches to Coreference Resolution. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguisticst, pp. 104–111 (2002)Google Scholar
  11. 11.
    Ng, V.: Unsupervised models for coreference resolution. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing 2008, pp. 640–649 (2008)Google Scholar
  12. 12.
    Kobdani, H., Schütze, H.: SUCRE: A Modular System for Coreference Resolution. In: Proceedings of the SemEval 2010, pp. 92–95 (2010)Google Scholar
  13. 13.
    Tjong Kim Sang, E.F.: Memory-Based Shallow Parsing. The Journal of Machine Learning Research, 559–594 (2002)Google Scholar
  14. 14.
    Fellbaum, C.: Wordnet: An Electronic Lexical Database. In: Brandford Books (1998)Google Scholar
  15. 15.
    Yianilos, P.N.: Normalized Forms for Two Common Metrics. In: Report 91-082-9027-1, NEC Research Institute (1991)Google Scholar
  16. 16.
    Ultsch, A., Siemon, H.P.: Kohonen’s Self Organizing Feature Maps for Exploratory Data Analysis. In: International Neural Networks Conference, pp. 305–308. Kluwer Academic Press, Paris (1990)Google Scholar
  17. 17.
    Vesanto, J.: SOM-based Data Visualization Methods. Intelligent Data Analysis 3, 111–126 (1999)CrossRefMATHGoogle Scholar
  18. 18.
    Cunningham, H., Maynard, D., Bontcheva, K., Tablan, V.: GATE: A framework and graphical development environment for robust NLP tools and applications. In: Proceedings of the 40th Anniversary Meeting of the Association for Computational Linguistics (2002)Google Scholar
  19. 19.
    Dimitrov, M.: Light-weight Approach to Coreference Resolution for Named Entities in Text. In: Mastersthesis, University of Sofia (2002)Google Scholar
  20. 20.
    Müller, C., Strube, M.: Multi-level annotation of linguistic data with MMAX2. In: Corpus Technology and Language Pedagogy: New Resources, New Tools, New Methods, pp. 197–214 (2006)Google Scholar
  21. 21.
    Versley, Y., Ponzetto, S.P., Poesio, M., Eidelman, V., Jern, A., Smith, J., Yang, X., Moschitti, A.: BART: a modular toolkit for coreference resolution. In: Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies, pp. 9–12 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Andre Burkovski
    • 1
  • Wiltrud Kessler
    • 1
  • Gunther Heidemann
    • 1
  • Hamidreza Kobdani
    • 2
  • Hinrich Schütze
    • 2
  1. 1.Intelligent Systems GroupUniversity of StuttgartStuttgartGermany
  2. 2.Institute for Natural Language ProcessingUniversity of StuttgartStuttgartGermany

Personalised recommendations