skip to main content
10.3115/1075096.1075117dlproceedingsArticle/Chapter ViewAbstractPublication PagesaclConference Proceedingsconference-collections
Article
Free Access

Minimum error rate training in statistical machine translation

Published:07 July 2003Publication History

ABSTRACT

Often, the training procedure for statistical machine translation models is based on maximum likelihood or related criteria. A general problem of this approach is that there is only a loose relation to the final translation quality on unseen text. In this paper, we analyze various training criteria which directly optimize translation quality. These training criteria make use of recently proposed automatic evaluation metrics. We describe a new algorithm for efficient training an unsmoothed error count. We show that significantly better results can often be obtained if the final evaluation criterion is taken directly into account as part of the training procedure.

References

  1. Srinivas Bangalore, O. Rambox, and S. Whittaker. 2000. Evaluation metrics for generation. In Proceedings of the International Conference on Natural Language Generation, Mitzpe Ramon, Israel. Google ScholarGoogle ScholarDigital LibraryDigital Library
  2. George Doddington. 2002. Automatic evaluation of machine translation quality using n-gram co-occurrence statistics. In Proc. ARPA Workshop on Human Language Technology.Google ScholarGoogle ScholarDigital LibraryDigital Library
  3. Richhard O. Duda and Peter E. Hart. 1973. Pattern Classification and Scene Analysis. John Wiley, New York, NY. Google ScholarGoogle ScholarDigital LibraryDigital Library
  4. Joshua Goodman. 1996. Parsing algorithms and metrics. In Proceedings of the 34th Annual Meeting of the ACL, pages 177--183, Santa Cruz, CA, June. Google ScholarGoogle ScholarDigital LibraryDigital Library
  5. B. H. Juang, W. Chou, and C. H. Lee. 1995. Statistical and discriminative methods for speech recognition. In A. J. Rubio Ayuso and J. M. Lopez Soler, editors, Speech Recognition and Coding - New Advances and Trends. Springer Verlag, Berlin, Germany.Google ScholarGoogle Scholar
  6. Shankar Kumar and William Byrne. 2002. Minimum bayes-risk alignment of bilingual texts. In Proc. of the Conference on Empirical Methods in Natural Language Processing, Philadelphia, PA. Google ScholarGoogle ScholarDigital LibraryDigital Library
  7. Sonja Nießen, Franz J. Och, G. Leusch, and Hermann Ney. 2000. An evaluation tool for machine translation: Fast evaluation for machine translation research. In Proc. of the Second Int. Conf. on Language Resources and Evaluation (LREC), pages 39--45, Athens, Greece, May.Google ScholarGoogle Scholar
  8. Franz Josef Och and Hermann Ney. 2002. Discriminative training and maximum entropy models for statistical machine translation. In Proc. of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), Philadelphia, PA, July. Google ScholarGoogle ScholarDigital LibraryDigital Library
  9. Franz J. Och, Christoph Tillmann, and Hermann Ney. 1999. Improved alignment models for statistical machine translation. In Proc. of the Joint SIGDAT Conf. on Empirical Methods in Natural Language Processing and Very Large Corpora, pages 20--28, University of Maryland, College Park, MD, June. Google ScholarGoogle ScholarDigital LibraryDigital Library
  10. Chris Paciorek and Roni Rosenfeld. 2000. Minimum classification error training in exponential language models. In NIST/DARPA Speech Transcription Workshop, May.Google ScholarGoogle Scholar
  11. Kishore A. Papineni, Salim Roukos, and R. T. Ward. 1997. Feature-based language understanding. In European Conf. on Speech Communication and Technology, pages 1435--1438, Rhodes, Greece, September.Google ScholarGoogle Scholar
  12. Kishore A. Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2001. Bleu: a method for automatic evaluation of machine translation. Technical Report RC22176 (W0109-022), IBM Research Division, Thomas J. Watson Research Center, Yorktown Heights, NY, September.Google ScholarGoogle Scholar
  13. Kishore A. Papineni. 1999. Discriminative training via linear programming. In Proceedings of the 1999 IEEE International Conference on Acoustics, Speech & Signal Processing, Atlanta, March. Google ScholarGoogle ScholarDigital LibraryDigital Library
  14. William H. Press, Saul A. Teukolsky, William T. Vetterling, and Brian P. Flannery. 2002. Numerical Recipes in C++. Cambridge University Press, Cambridge, UK.Google ScholarGoogle Scholar
  15. Ralf Schlüter and Hermann Ney. 2001. Model-based MCE bound to the true Bayes' error. IEEE Signal Processing Letters, 8(5):131--133, May.Google ScholarGoogle ScholarCross RefCross Ref
  16. Christoph Tillmann, Stephan Vogel, Hermann Ney, Alex Zubiaga, and Hassan Sawaf. 1997. Accelerated DP based search for statistical translation. In European Conf. on Speech Communication and Technology, pages 2667--2670, Rhodes, Greece, September.Google ScholarGoogle Scholar
  17. Nicola Ueffing, Franz Josef Och, and Hermann Ney. 2002. Generation of word graphs in statistical machine translation. In Proc. Conference on Empirical Methods for Natural Language Processing, pages 156--163, Philadelphia, PE, July. Google ScholarGoogle ScholarDigital LibraryDigital Library

Index Terms

  1. Minimum error rate training in statistical machine translation
      Index terms have been assigned to the content through auto-classification.

      Recommendations

      Comments

      Login options

      Check if you have access through your login credentials or your institution to get full access on this article.

      Sign in
      • Published in

        cover image DL Hosted proceedings
        ACL '03: Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
        July 2003
        571 pages

        Publisher

        Association for Computational Linguistics

        United States

        Publication History

        • Published: 7 July 2003

        Qualifiers

        • Article

        Acceptance Rates

        Overall Acceptance Rate85of443submissions,19%

      PDF Format

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader