Korma 2003: Newly Improved Korean Morpheme Analysis Module for Reducing Terminological and Spacing Errors in Document Analysis

  • Ho-cheol Choi
  • Sang-yong Han
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3406)


The paper describes the newly improved Korean morpheme analysis module KorMa 2003. This new module applies the custom user dictionary for analyzing new and unknown words and special terms and operates an automatic word spacing module during post-processing to prevent failures of sentence analysis due to incorrect spacing between words. KorMa 2003 has accuracy enhanced by 15% in comparison with the previously reported version.


Special Term Special Word Correct Word Unknown Word Compound Noun 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Gelbukh, A., Sidorov, G.: Morphological Analysis of Inflective Languages through Generation. Procesamiento de Lenguaje Natural (29), 105–112Google Scholar
  2. 2.
    Gelbukh, A., Sidorov, G.: Approach to construction of automatic morphological analysis systems for inflective languages with little effort. In: Gelbukh, A. (ed.) CICLing 2003. LNCS, vol. 2588, pp. 215–220. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  3. 3.
    Hwang, D., Choi, K., Kim, T.: Natural Language ProcessingGoogle Scholar
  4. 4.
    Kwak, J., Eun, J.J., Kang, Y.S.: Structure and Characteristics of LGKNA. In: 1st workshop on Evaluation of Morpheme Analysis and TaggingGoogle Scholar
  5. 5.
    Lee, S., Kim, D., Seo, J., Choi, K., Kim, G.: Construction and Analysis of Korean Morpheme based on two-level model. In: Proc. of KISS Fall Conference, vol. 19Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Ho-cheol Choi
    • 1
  • Sang-yong Han
    • 1
  1. 1.Graduate School of InformationChungang UniversityKorea

Personalised recommendations