Advertisement

Comparing and Integrating Alignment Template and Standard Phrase-Based Statistical Machine Translation

  • Lin Xu
  • Xiaoguang Cao
  • Bufeng Zhang
  • Mu Li
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4394)

Abstract

In statistical machine translation (SMT) research, phrase-based methods have been receiving more interest in recent years. In this paper, we first give a brief survey of phrase-based SMT framework, and then make detailed comparisons of two typical implementations: alignment template approach and standard phrase-based approach. At last, we propose an improved model to integrate alignment template into standard phrase-based SMT as a new feature in a log-linear model. Experimental results show that our method outperforms the baseline method.

Keywords

Target Sentence Training Corpus Statistical Machine Translation Name Entity Test Corpus 
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. 1.
    Tomás, J., Casacuberta, F.: Combining Phrase-based and Template-Based alignment models in Statistical Translation. In: IbPRIA (2003)Google Scholar
  2. 2.
    Brown, P.F., et al.: The methematics of statistical machine translation:Parameter estimation. Computational Linguistics (1999)Google Scholar
  3. 3.
    Och, F.J.: Improved Alignment Models for Statistical Machine Translation. In: Proc. of the Joint Conf. of Empirical Methods in Natural Language Processing and Very Large Corpora, June (1999)Google Scholar
  4. 4.
    Yamada, K., Knight, K.: A syntax-based statistical translation model. In: Proc. Of the 39th Annual Meeting of ACL, Toulouse, France, July (2001)Google Scholar
  5. 5.
    Marcu, D., Wong, W.: A phrase-based, joint probability model for statistical machine translation. In: Proceeding of EMNLP (2002)Google Scholar
  6. 6.
    Zens, R., Och, F.J., Ney, H.: Phrase-based Statistical Machine Translation. In: Jarke, M., Koehler, J., Lakemeyer, G. (eds.) 25th German Conf. on Artificial Intelligence, KI2002 (2002)Google Scholar
  7. 7.
    Koehn, P., et al.: Statistical Phrase-Based Translation. In: HLT/NAACL (2003)Google Scholar
  8. 8.
    Och, F.J., Ney, H.: Discriminative Training and Maximum Entropy Models for Statistical Machine Translation. In: ACL (2002)Google Scholar
  9. 9.
    Och, F.J., Ney, H.: The alignment template approach to statistical machine translation. Accepted for publication in Computational Linguistics (2004)Google Scholar
  10. 10.
    Koehn, P., et al.: Edinburgh System Description for 2005 IWSLT Speech Translation Evaluation (2005)Google Scholar
  11. 11.
    Kumar, S., et al.: A weighted finite state transducer translation template model for statistical machine translation. Natural Language Engineering 1(1), 1–41 (2004)Google Scholar
  12. 12.
    Birch Mayne, A.C.: Scalable Phrase-Based, Joint Probability Model for Statistical Machine Translation. Master of Science Cognitive Science and Natural Language Processing School of Informatics University of Edinburgh (2005)Google Scholar
  13. 13.
    Chiang, D.: A hierarchical Phrase-Based Model for Statistical Machine Translation. In: Proc. Of the 43rd Annual Meeting of the ACL, June (2005)Google Scholar
  14. 14.
    Papineni, K.: BLEU: a Method for Automatic Evaluation of Machine Translation. In: Proc. Of the 40th ACL, July (2002)Google Scholar
  15. 15.
    Och, F.J.: GIZA++: Training of statistical translation models (2000), http://www-i6.informatik.rwth-aachen.de/~och/softeware/GIZA++.html
  16. 16.
    Koehn, P.: Pharaoh:Training Manual (2004)Google Scholar
  17. 17.
    Och, F.J.: Minimum Error Rate Training in Statistical Machine Translation. In: ACL (2003)Google Scholar
  18. 18.
    Koehn, P.: Pharaoh: a Beam Search Decoder for Phrased-based Statsistical Machine Translation Models, User Mannual and Description for version 1.2, Technical report, USC Information Science Institute (August 2004)Google Scholar
  19. 19.
    Och, F.J.: An Efficient Method for Determining Bilingual Word Classes. In: Proceedings of EACL (1999)Google Scholar
  20. 20.
    Xiong, D., Liu, Q., Lin, S.: Maximum Entropy Based Phrase Reordering Model for Statistical Machine Translation. In: ACL (2006)Google Scholar
  21. 21.
    Al-Onaizan, Y., Papineni, K.: Distortion Models for Statistical Machine Translation. In: ACL (2006)Google Scholar
  22. 22.
    Arun, A., et al.: Edinburgh System Description for the 2006 TC-STAR Spoken LanguageTranslation Evaluation (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Lin Xu
    • 1
  • Xiaoguang Cao
    • 1
  • Bufeng Zhang
    • 2
  • Mu Li
    • 3
  1. 1.Lab of Pattern Recognition and Intelligent System, Image Processing Center, BeiHang UniversityChina
  2. 2.AI Lab, Computer Science and Technology, Tianjing UniversityChina
  3. 3.Microsoft Research AsiaChina

Personalised recommendations