Improvement of Translation Accuracy for the Outlines of Japanese Statutes by Splitting Parenthesized Expressions

Authors

  • Kouhei Okada Nagoya University
  • Yasuhiro Ogawa
  • Makoto Nakamura
  • Tomohiro Ohno
  • Katsuhiko Toyama

Abstract

To globally share Japanese legal information, we translate the Outlines of Japanese statutes. These outlines are the official summaries of Japanese statutes and are useful to quickly understand their contents. In a previous statistical machine translation system for the outlines, we found that the training corpus consisted of both statutes and their outlines, including many long sentences that reduced the translation quality. To solve this problem, we shortened the length of sentences and focused on parenthesized expressions. In this paper, we propose a translation method that splits off parenthesized expressions from the sentences. Experimental result shows the effectiveness of our method.

References

Greenleaf, G. Legal Information Institutes and the Free Access to Law Movement, GlobaLex website, 2008.

GYOSEI Corporation Legislation Seminar, Zusetsu Houseishitsumu Nyumon, GYO-SEI Corporation, 2013 (in Japanese) .

Hoshino, S., Miyao, Y., Sudoh, K., and Nagata, M. Two-Stage Pre-ordering for Japanese-to-English Statistical Machine Translation, Proc. of IJCNLP 2013, pp. 1062-1066, 2013.

Inagi, D., Ogawa, Y., Nakamura, M., Ohno, T., and Toyama, K. Statistical Machine Translation for Outlines of Japanese Statutes, Proc. of JURISIN 2013, pp. 37-49, 2013.

Isozaki, H., Hirao, T., Duh, K., Sudoh, K., and Tsukada, H. Automatic Evaluation of Translation Quality for Distant Language Pairs, Proc. of EMNLP 2010, pp. 944-952, 2010.

Kawachi, G., Ogawa, Y., Nakamura, M., Ohno, T., and Toyama, K. Daily News on Japanese Legislation toward International Sharing of Japanese Legal Information, Journal of Open Access to Law, Vol. 3, No. 1, 19 pages, 2015.

Koehn, P. Statistical Machine Translation, Cambridge University Press, 2010.

Koehn, P., Hoang, H., Birch, A., Callison-Burch, C., Federico, M., Bertoldi, N., Cowan, B., Shen, W., Moran, C., Zens, R., Dyer, C., Bojar, O., Constanin, A., and Herbst, E. Moses: Open Source Toolkit for Statistical Machine Translation, Proc. of ACL2007, pp. 177-180, 2007.

Kudo, T., Yamamoto, K., and Matsumoto, Y. Applying Conditional Random Fields to Japanese Morphological Analysis, Proc. of EMNLP 2004, pp. 230-237, 2004.

Och, F. J. Minimum Error Rate Training in Statistical Machine Translation, Proc. of ACL 2003, pp. 160{167, 2003.

Och, F. J. and Ney, H. A Systematic Comparison of Various Statistical Alignment Models, Computational Linguistics, Vol. 29, No. 1, pp. 19-51, 2005.

Ogawa, Y., Inagi, D., Nakamura, M., and Toyama, K. Translation for Outlines of Japanese Acts, Law via the Internet 2013, 12 pages, 2013.

Papineni, K., Roukos, S., Ward, T., and Zhu, W. BLEU: A Method for Automatic Evaluation of Machine Translation, Proc. of ACL 2002, pp. 138-145, 2002.

Stolcke, A. SRILM - An Extensible Language Modeling Toolkit, Proc. of ICSLP 2002, pp. 901-904, 2002.

Toyama, K., Saito, D., Sekine, Y., Ogawa, Y., Kakuta, T., Kimura, T., and Matsuura, Y. Design and Development of Japanese Law Translation Database System, Law via the Internet 2011, 12 pages, 2011.

Downloads

Published

2016-03-01

Issue

Vol. 4 No. 1 (2016)

Section

Data organization and legal informatics

License

Copyright Agreement with Authors

Authors submitting a paper to JOAL automatically agree to confer a limited license to JOAL if and when the manuscript is accepted for publication. This license allows JOAL to publish a manuscript in a given issue, by any means, anywhere in the world. Authors whose submissions have been accepted then have a choice of:

  1. Dedicating the article to the public domain. This allows anyone to make any use of the article at any time, including commercial use. A good way to do this is to use the Creative Commons Public Domain Dedication Web form; see http://creativecommons.org/license/publicdomain-2?lang=en.
  2. Retaining some rights while allowing some use. For example, authors may decide to disallow commercial use without permission. Authors may also decide whether to allow users to make modifications (e.g.translations, adaptations) without permission. A good way to make these choices is to use a Creative Commons license.
    • Go to http://creativecommons.org/license/.
    • Choose and select license. Choose "generic" if you are in the U.S. and "text" for JOAL articles.
    • What to do next — you can then e–mail the license html code to yourself. Do this, and then forward that e–mail to JOAL’s editors. Put your name in the subject line of the e–mail with your name and article title in the e–mail.
    Background information about Creative Commons licenses can be found at http://creativecommons.org/about/licenses/.
  3. Retaining full rights, including translation and reproduction rights. Authors may use the statement:  © Author 2013 All Rights Reserved. Authors may choose to use their own wording to reserve copyright. If you choose to retain full copyright, please add your copyright statement to the end of the article.