Skip to main content
SpringerLink
Log in

On-Line Error Detection of Annotated Corpus Using Modular Neural Networks

  • Conference paper
  • First Online:
Artificial Neural Networks — ICANN 2001 (ICANN 2001)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 2130))

Included in the following conference series:

Abstract

This paper proposes an on-line error detecting method for a manually annotated corpus using min-max modular (M3) neural networks. The basic idea of the method is to use guaranteed convergence of the M3 network to detect errors in learning data. To confirm the effectiveness of the method, a preliminary computer experiment was performed on a small Japanese corpus containing 217 sentences. The results show that the method can not only detect errors within a corpus, but may also discover some kinds of knowledge or rules useful for natural language processing.

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 149.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 189.00
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. Merialdo, B.: Tagging English text with a probabilistic model, Computational Linguistics, Vol. 20, No. 2, pp. 155–171, 1994.

    Google Scholar 

  2. Brill, E.: Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging, Computational Linguistics, Vol. 21, No. 4, pp. 543–565, 1994.

    Google Scholar 

  3. Ma, Q., Uchimoto, K., Murata, M., and Isahara, H: Hybrid neuro and rule-based part of speech taggers, Proc. COLING’2000, Saarbrücken, pp. 509–515, 2000.

    Google Scholar 

  4. Lu, B. L. and Ito, M.: Task decomposition and module combination based on class relations: a modular neural network for pattern classification, IEEE Trans. Neural Networks, Vol. 10, No. 5, pp. 1244–1256, 1999.

    Article  Google Scholar 

  5. Lu, B. L., Ma, Q., Isahara, H., and Ichikawa M.: Efficient part-of-speech tagging with a min-max module neural network model, to appear in Applied Intelligence, 2001.

    Google Scholar 

  6. Eskin, E.: Detecting errors within a corpus using anomaly detection, Proc. NAACL’ 2000, Seattle, pp. 148–153, 2000.

    Google Scholar 

  7. Murata, M, Utiyama, M., Uchimoto, K., and Ma, Q., and Isahara, H.: Corpus error detection and correction using the decision-list and example-based methods, Proc. Information Processing Society of Japan, WGNL 136-7, pp. 49–56, 2000 (in Japanese).

    Google Scholar 

  8. Kurohashi, S. and Nagao, M: Kyoto University text corpus project, Proc. 3rd Annual Meeting of the Association for Natural Language Processing, pp. 115–118, 1997 (in Japanese).

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Communications Research Laboratory, Kyoto, 619-0289, Japan

    Qing Ma, Masaki Murata & Hitoshi Isahara

  2. Brain Science Institute, RIKEN, Wako, 351-0198, Japan

    Bao-Liang Lu & Michnori Ichikawa

Authors
  1. Qing Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bao-Liang Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Masaki Murata
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Michnori Ichikawa
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hitoshi Isahara
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Dept. of Mecidal Cybernetics and Artificial Intelligence, University of Vienna, Freyung 6/2, 1010, Vienna, Austria

    Georg Dorffner

  2. Institute for Computer Aided Automation Pattern Recognition and Image Processing Group, Technical University of Vienna, Favoritenstr. 9/1832, 1040, Vienna, Austria

    Horst Bischof

  3. Institut für Statistik, Wirtschaftsuniversität Wien, Augasse 2-6, 1090, Wien, Austria

    Kurt Hornik

Rights and permissions

Reprints and permissions

Copyright information

© 2001 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Ma, Q., Lu, BL., Murata, M., Ichikawa, M., Isahara, H. (2001). On-Line Error Detection of Annotated Corpus Using Modular Neural Networks. In: Dorffner, G., Bischof, H., Hornik, K. (eds) Artificial Neural Networks — ICANN 2001. ICANN 2001. Lecture Notes in Computer Science, vol 2130. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44668-0_165

Download citation

  • DOI: https://doi.org/10.1007/3-540-44668-0_165

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-42486-4

  • Online ISBN: 978-3-540-44668-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation