WRITING SUPPORT SYSTEM DEALING WITH NOTATIONAL VARIANT SELECTION

Aya Nishikawa, Ryo Nishimura, Yasuhiko Watanabe, Yoshihiro Okada

2009

Abstract

In Japanese, there are a large number of notational variants of words. This is because Japanese words are written in three kinds of characters: Kanji (Chinese) characters, Hiragara letters, and Katakana letters. Japanese students study basic rules of Japanese writing in school for many years. However, it is difficult to learn which notational variant is suitable for official, business, and technical documents because the rules have many exceptions. From the viewpoint of information retrieval, a considerable number of studies have been made on notational variants, however, previous Japanese writing support systems were not concerned with them sufficiently. This is because their main purposes were misspelling detection. Nondominant notational variants are not misspelling, but often unsuitable for official, business, or technical documents. To solve this problem, we developed a writing support system which detects nondominant notational variants in students’ reports and shows dominant ones to the students. This system is based on the idea that suitable notational variants are used dominantly in official, business, and technical documents. In this study, we first show the diversity of notational variants of Japanese words and how to develop notational variant dictionaries by which our system determines which notational variant is dominant in official, business, and technical documents. Finally, we conducted a control experiment and show the effectiveness of our system.

References

  1. Kubomura and Kameda: Information Retrieval System with Abilities of Processing Katakana-Allographs, Trans. of IEICE, Vol.J86-D-II, No.3, (2003).
  2. Kouda: Search method of variant notations on a science and technology document retrieval system, IPSJ SIG NL, Vol.2006, No.118, (1993).
  3. Bamba, Shinzato, and Kurohashi: Development of a Largescale Web Page Clustering System using an Open Search Engine Infrastructure TSUBAKI, IPSJ SIG NL, Vol.2008, No.4, (1993).
  4. Shimomura, Namiki, Nakagawa, and Takahashi: A method for detecting errors in Japanese sentences based on morphological analysis using minimal cost path search, Trans. of IPSJ, Vol.33, No.4, (1992).
  5. Araki, Ikehara, and Tukahara: A method for detecting and correcting of characters wrongly substituted, deleted or inserted in Japanese strings using 2nd-order Markov model, IPSJ SIG NL, Vol.93, No.79, (1993).
  6. Murata and Isahara: Extraction of negative examples based on positive examples: automatic detection of misspelled Japanese expressions and relative clauses that do not have case relations with their heads, IPSJ SIG NL, Vol.2001, No.69, (2001).
  7. Yokoyama: Can we predict preference for kanji form from newspaper data on character frequency?, IPSJ SIG CH, Vol.2006, No.10, (2006).
  8. Kurohashi and Kawahara: JUMAN Manual version 5.1 (in Japanese), Kyoto University, (2005).
  9. Mainichi Shinbun CD-Rom data set 2006, Nichigai Associates Co., (2007).
  10. Landis and Koch: The measurement of observer agreement for categorical data, Biometrics, Vol. 33, (1977).
Download


Paper Citation


in Harvard Style

Nishikawa A., Nishimura R., Watanabe Y. and Okada Y. (2009). WRITING SUPPORT SYSTEM DEALING WITH NOTATIONAL VARIANT SELECTION . In Proceedings of the First International Conference on Computer Supported Education - Volume 1: CSEDU, ISBN 978-989-8111-82-1, pages 73-80. DOI: 10.5220/0001973800730080


in Bibtex Style

@conference{csedu09,
author={Aya Nishikawa and Ryo Nishimura and Yasuhiko Watanabe and Yoshihiro Okada},
title={WRITING SUPPORT SYSTEM DEALING WITH NOTATIONAL VARIANT SELECTION},
booktitle={Proceedings of the First International Conference on Computer Supported Education - Volume 1: CSEDU,},
year={2009},
pages={73-80},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001973800730080},
isbn={978-989-8111-82-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Computer Supported Education - Volume 1: CSEDU,
TI - WRITING SUPPORT SYSTEM DEALING WITH NOTATIONAL VARIANT SELECTION
SN - 978-989-8111-82-1
AU - Nishikawa A.
AU - Nishimura R.
AU - Watanabe Y.
AU - Okada Y.
PY - 2009
SP - 73
EP - 80
DO - 10.5220/0001973800730080