Advertisement

No Free Lunch in Factored Phrase-Based Machine Translation

  • Aleš Tamchyna
  • Ondřej Bojar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7817)

Abstract

Factored models have been successfully used in many language pairs to improve translation quality in various aspects. In this work, we analyze this paradigm in an attempt at automating the search for well-performing machine translation systems. We examine the space of possible factored systems, concluding that a fully automatic search for good configurations is not feasible. We demonstrate that even if results of automatic evaluation are available, guiding the search is difficult due to small differences between systems, which are further blurred by randomness in tuning. We describe a heuristic for estimating the complexity of factored models. Finally, we discuss the possibilities of a “semi-automatic” exploration of the space in several directions and evaluate the obtained systems.

Keywords

Machine Translation Generation Step Free Lunch Statistical Machine Translation Parallel 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.
    Koehn, P., Och, F.J., Marcu, D.: Statistical phrase-based translation. In: HLT/NAACL (2003)Google Scholar
  2. 2.
    Koehn, P., Hoang, H.: Factored translation models. In: EMNLP-CoNLL, pp. 868–876. ACL (2007)Google Scholar
  3. 3.
    Bojar, O.: English-to-Czech Factored Machine Translation. In: Proc. of ACL WMT, Prague, Czech Republic, pp. 232–239. ACL (2007)Google Scholar
  4. 4.
    Avramidis, E., Koehn, P.: Enriching morphologically poor languages for statistical machine translation. In: Proc. of ACL/HLT, Columbus, Ohio, pp. 763–770. ACL (2008)Google Scholar
  5. 5.
    Badr, I., Zbib, R., Glass, J.: Segmentation for English-to-Arabic statistical machine translation. In: Proc. of ACL/HLT Short Papers, Columbus, Ohio, pp. 153–156. ACL (2008)Google Scholar
  6. 6.
    Ramanathan, A., Choudhary, H., Ghosh, A., Bhattacharyya, P.: Case markers and morphology: addressing the crux of the fluency problem in English-Hindi SMT. In: Proc. of ACL/IJCNLP, Suntec, Singapore, vol. 2, pp. 800–808. ACL (2009)Google Scholar
  7. 7.
    Koehn, P., Haddow, B., Williams, P., Hoang, H.: More linguistic annotation for statistical machine translation. In: Proc. of WMT and MetricsMATR, Uppsala, Sweden, pp. 115–120. ACL (2010)Google Scholar
  8. 8.
    Yeniterzi, R., Oflazer, K.: Syntax-to-Morphology Mapping in Factored Phrase-Based Statistical Machine Translation from English to Turkish. In: Proc. of ACL, Uppsala, Sweden, pp. 454–464. ACL (2010)Google Scholar
  9. 9.
    Birch, A., Osborne, M., Koehn, P.: CCG Supertags in Factored Statistical Machine Translation. In: Proc. of ACL WMT, Prague, Czech Republic, pp. 9–16. ACL (2007)Google Scholar
  10. 10.
    Stymne, S.: German Compounds in Factored Statistical Machine Translation. In: Nordström, B., Ranta, A. (eds.) GoTAL 2008. LNCS (LNAI), vol. 5221, pp. 464–475. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  11. 11.
    Koehn, P., Schroeder, J.: Experiments in domain adaptation for statistical machine translation. In: Proc. of ACL WMT, Prague, Czech Republic, pp. 224–227. ACL (2007)Google Scholar
  12. 12.
    Niehues, J., Waibel, A.: Domain adaptation in statistical machine translation using factored translation models. In: EAMT (2010)Google Scholar
  13. 13.
    Santorini, B.: Part-of-Speech Tagging Guidelines for the Penn Treebank Project. In: University of Pennsylvania, School of Engineering and Applied Science, Dept. of Computer and Information Science, Philadelphia (1990)Google Scholar
  14. 14.
    Hajič, J., Panevová, J., Hajičová, E., Sgall, P., Pajas, P., Štěpánek, J., Havelka, J., Mikulová, M., Žabokrtský, Z., Ševčíková Razímová, M.: Prague Dependency Treebank 2.0. LDC2006T01 (2006) ISBN: 1-58563-370-4Google Scholar
  15. 15.
    Och, F.J., Ney, H.: Improved statistical alignment models. In: ACL. ACL (2000)Google Scholar
  16. 16.
    Stolcke, A.: SRILM - an extensible language modeling toolkit. In: Proc. of ICSLP2002 - INTERSPEECH. ISCA, Denver (2002)Google Scholar
  17. 17.
    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., Constantin, A., Herbst, E.: Moses: Open Source Toolkit for Statistical Machine Translation. In: Proc. of ACL: Demo and Poster Sessions, Prague, Czech Republic, pp. 177–180. ACL (June 2007)Google Scholar
  18. 18.
    Bojar, O., Jawaid, B., Kamran, A.: Probes in a Taxonomy of Factored Phrase-Based Models. In: Proc. of ACL WMT, Montréal, Canada, pp. 253–260. ACL (2012)Google Scholar
  19. 19.
    Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: A method for automatic evaluation of machine translation. In: ACL, pp. 311–318. ACL (2002)Google Scholar
  20. 20.
    Och, F.J.: Minimum error rate training in statistical machine translation. In: Proc. of ACL, Sapporo, Japan, pp. 160–167. ACL (2003)Google Scholar
  21. 21.
    Hopkins, M., May, J.: Tuning as ranking. In: EMNLP, pp. 1352–1362. ACL (2011)Google Scholar
  22. 22.
    Bojar, O., Žabokrtský, Z.: CzEng0.9: Large Parallel Treebank with Rich Annotation. Prague Bulletin of Mathematical Linguistics 92 (2009)Google Scholar
  23. 23.
    Koehn, P.: Statistical Significance Tests for Machine Translation Evaluation. In: Proc. of EMNLP, Barcelona, Spain (2004)Google Scholar
  24. 24.
    Clark, J.H., Dyer, C., Lavie, A., Smith, N.A.: Better hypothesis testing for statistical machine translation: Controlling for optimizer instability. In: Proc. of ACL (Short Papers), pp. 176–181. ACL (2011)Google Scholar
  25. 25.
    Bojar, O., Žabokrtský, Z., Dušek, O., Galuščáková, P., Majliš, M., Mareček, D., Maršík, J., Novák, M., Popel, M., Tamchyna, A.: The Joy of Parallelism with CzEng 1.0. In: Proc. of LREC, İstanbul, Turkey, pp. 3921–3928. ELRA (2012)Google Scholar
  26. 26.
    Callison-Burch, C., Koehn, P., Monz, C., Zaidan, O.: Findings of the 2011 Workshop on Statistical Machine Translation. In: Proc. of ACL WMT, Edinburgh, Scotland, pp. 22–64. ACL (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Aleš Tamchyna
    • 1
  • Ondřej Bojar
    • 1
  1. 1.Institute of Formal and Applied LinguisticsPrahaCzech Republic

Personalised recommendations