Advertisement

Statistical Methods for Machine Translation

  • Stephan Vogel
  • Franz Josef Och
  • Christof Tillmann
  • Sonja Nießen
  • Hassan Sawaf
  • Hermann Ney
Part of the Artificial Intelligence book series (AI)

Abstract

In this article we describe the statistical approach to machine translation as implemented in the stattrans module of the Verbmobil system. The statistical translation approach uses two types of information: a translation model and a language model. The language model used is an m-gram model. The translation model comprises a stochastic lexicon and word position parameters. To capture dependencies between word groups in each of the two languages, alignment templates are used. We describe the components of the system and report results on the Verbmobil task. The experience obtained in the Verbmobil project shows that the statistical approach is very competitive with other translation approaches.

Keywords

Target Word Language Model Machine Translation Target Language Target Sentence 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Batliner, A., Buckow, J., Niemann, H., Nöth, E., and Warnke, V. The Prosody Module. In this volume. Google Scholar
  2. Brown, P.F., Delia Pietra, S.A., Delia Pietra, V.J., and Mercer, R.L. (1993). The Mathematics of Statistical Machine Translation: Parameter Estimation. Computational Linguistics 19(2):263–311.Google Scholar
  3. Dagan, I., Church, K., and Gale, W.A. (1993). Robust Bilingual Word Alignment for Ma-chine Aided Translation. In Proceedings of the Workshop on Very Large Corpora, 1–8, Columbus, Ohio, June.Google Scholar
  4. Kay, M., and Roscheisen, M. (1993). Text-Translation Alignment. Computational Linguistics 19(1): 121–142.Google Scholar
  5. Melamed, I. D. (1998). Manual Annotation of Translational Equivalence: The Blinker Project. Institute for Research in Cognitive Science Technical Report #98–07, University of Pennsylvania, Philadelphia, PA.Google Scholar
  6. Ney, H., NieBen, S., Och, F.J., Sawaf, H., Tillmann, C. and Vogel, S. (2000). Algorithms for Statistical Translation of Spoken Language. IEEE Transactions on Speech and Audio Processing 8(1):24–36, January.CrossRefGoogle Scholar
  7. Nießen, S., Vogel, S., Ney, H., and Tillmann, C. (1998). A DP Based Search Algorithm for Statistical Machine Translation. In Proceedings of COLING-ACL ’98: 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, 960–967, Montreal, Quebec, Canada, August.Google Scholar
  8. Nießen, S., Och, F. J., Leusch, G., and Ney, H. (2000). An Evaluation Tool for Machine Translation: Fast Evaluation for MT Research. In Proceedings of the Second Interna-tional Conference on Language Resources and Evaluation, 39–45, Athens, Greece, May.Google Scholar
  9. Nießen, S., and Ney, H. (2000). Improving SMT Quality with Morpho-Syntactical Analysis. In Proceedings of COLING 2000: The 18th International Conference on Computational Linguistics, Saarbriicken, Germany, July.Google Scholar
  10. Och, F. J. (1999). An Efficient Method to Determine Bilingual Word Classes. In Proceed-ings of EACL ’99: Ninth Conferebce of the European Chapter of the Association for Computational Linguistics, 71–76, Bergen, Norway, June.Google Scholar
  11. Och, F.J., Tillmann, C, and Ney, H. (1999). Improved Alignment Models for Statistical Machine Translation. In Proceedings of the 1999 Joint S1GDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, 20–28, University of Maryland, College Park, Maryland, June.Google Scholar
  12. Och, F. J., and Ney, H. (2000). A Comparison of Alignment Models for Statistical Machine Translation. In Proceedings of COLING 2000: The 18th International Conference on Computational Linguistics, Saarbrücken, Germany, July.Google Scholar
  13. Sawaf, H., Schütz, K., and Ney, H. (2000). On the Use of Grammar Based Language Models for Statistical Machine Translation. In Proceedings of 6th International Workshop on Parsing Technologies, 231–241, Trento, Italy, February.Google Scholar
  14. Spilker, J., Klarner, M., and Görz, G. Processing Self-Corrections in a Speech-to-Speech System. In this volume. Google Scholar
  15. Tessiore, L., and v. Hahn, W. Functional Validation of a Machine Interpretation System: Verbmobil. In this volume. Google Scholar
  16. Tillmann, C, Vogel, S., Ney, H., and Zubiaga, A. (1997). A DP-Based Search Using Mono-tone Alignments in Statistical Translation. In Proceedings of the 35th Annual Conference of the Association for Computational Linguistics, 289–296, Madrid, Spain, July.CrossRefGoogle Scholar
  17. Vogel, S., Ney, H., and Tillmann, C. (1996). HMM-Based Word Alignment in Statistical Translation. In Proceedings of COLTNG ’96: The 16th International Conference on Computational Linguistics, 836–841, Copenhagen, Denmark, August.CrossRefGoogle Scholar
  18. Vogel, S., NieBen, S., and Ney H. (2000). Automatic Extrapolation of Human Assessment of Translation Quality. In Second International Conference on Language Resources and Evaluation, Workshop Proceedings: Evaluation of Machine Translation, 35–39, Athens, Greece, May.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Stephan Vogel
    • 1
  • Franz Josef Och
    • 1
  • Christof Tillmann
    • 1
  • Sonja Nießen
    • 1
  • Hassan Sawaf
    • 1
  • Hermann Ney
    • 1
  1. 1.Lehrstuhl für Informatik VI, Computer Science DepartmentRWTH Aachen-University of TechnologyGermany

Personalised recommendations