Advertisement

Machine Translation

, 25:145 | Cite as

GREAT: open source software for statistical machine translation

  • Jorge GonzálezEmail author
  • Francisco Casacuberta
Article

Abstract

In this article, the first public release of GREAT as an open-source, statistical machine translation (SMT) software toolkit is described. GREAT is based on a bilingual language modelling approach for SMT, which is so far implemented for n-gram models based on the framework of stochastic finite-state transducers. The use of finite-state models is motivated by their simplicity, their versatility, and the fact that they present a lower computational cost, if compared with other more expressive models. Moreover, if translation is assumed to be a subsequential process, finite-state models are enough for modelling the existing relations between a source and a target language. GREAT includes some characteristics usually present in state-of-the-art SMT, such as phrase-based translation models or a log-linear framework for local features. Experimental results on a well-known corpus such as Europarl are reported in order to validate this software. A competitive translation quality is achieved, yet using both a lower number of model parameters and a lower response time than the widely-used, state-of-the-art SMT system Moses.

Keywords

Statistical machine translation Monotonic bilingual segmentation Grammatical inference Language modelling Stochastic finite-state transducers 

References

  1. Amengual JC, Benedí JM, Casacuberta F, Castaño MA, Castellanos A, Jiménez VM, Llorens D, Marzal A, Pastor M, Prat F, Vidal E, Vilar JM (2000) The EUTRANS-I speech translation system. Mach Transl 15(1-2): 75–103zbMATHCrossRefGoogle Scholar
  2. Andrés-Ferrer J, Juan-Císcar A, Casacuberta F (2008) Statistical estimation of rational transducers applied to machine translation. Appl Artif Intell 22(1–2): 4–22CrossRefGoogle Scholar
  3. Bangalore S, Riccardi G (2002) Stochastic finite-state models for spoken language machine translation. Mach Transl 17(3): 165–184CrossRefGoogle Scholar
  4. Berstel J (1979) Transductions and context-free languages. B.G. Teubner, Stuttgart, GermanyzbMATHGoogle Scholar
  5. Casacuberta F, Vidal E (2004) Machine translation with inferred stochastic finite-state transducers. Comput Linguist 30(2): 205–225MathSciNetCrossRefGoogle Scholar
  6. Casacuberta F, Vidal E (2007) Learning finite-state models for machine translation. Mach Learn 66(1): 69–91CrossRefGoogle Scholar
  7. Foster G, Kuhn R, Johnson H (2006) Phrasetable smoothing for statistical machine translation. In: Proceedings of the 11th Conference on Empirical Methods in Natural Language Processing, Stroudsburg, PA, pp 53–61Google Scholar
  8. González J (2009) Aprendizaje de transductores estocásticos de estados finitos y su aplicación en traducción automática. PhD thesis, Universitat Politècnica de València. Advisor: Casacuberta FGoogle Scholar
  9. González J, Casacuberta F (2009) GREAT: a finite-state machine translation toolkit implementing a grammatical inference approach for transducer inference (GIATI). In: Proceedings of the EACL Workshop on Computational Linguistic Aspects of Grammatical Inference, Athens, Greece, pp 24–32Google Scholar
  10. Kanthak S, Vilar D, Matusov E, Zens R, Ney H (2005) Novel reordering approaches in phrase-based statistical machine translation. In: Proceedings of the ACL Workshop on Building and Using Parallel Texts: Data-Driven Machine Translation and Beyond, Ann Arbor, MI, pp 167–174Google Scholar
  11. Karttunen L (2001) Applications of finite-state transducers in natural language processing. In: Proceedings of the 5th Conference on Implementation and Application of Automata, London, UK, pp 34–46Google Scholar
  12. Kneser R, Ney H (1995) Improved backing-off for n-gram language modeling. In: Proceedings of the 20th IEEE International Conference on Acoustic, Speech and Signal Processing, Detroit, MI, pp 181–184Google Scholar
  13. Knight K, Al-Onaizan Y (1998) Translation with finite-state devices. In: Proceedings of the 3rd Conference of the Association for Machine Translation in the Americas, Langhorne, PA, pp 421–437Google Scholar
  14. Koehn P (2004) Statistical significance tests for machine translation evaluation. In: Proceedings of the 9th Conference on Empirical Methods in Natural Language Processing, Barcelona, Spain, pp 388–395Google Scholar
  15. Koehn P (2005) Europarl: a parallel corpus for statistical machine translation. In: Proceedings of the 10th Machine Translation Summit, Phuket, Thailand, pp 79–86Google Scholar
  16. Koehn P (2010) Statistical machine translation. Cambridge University Press, Cambridge, UKzbMATHGoogle Scholar
  17. Koehn P, Hoang H (2007) Factored translation models. In: Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Prague, Czech Republic, pp 868–876Google Scholar
  18. 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 (2007) Moses: open source toolkit for statistical machine translation. In: Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, Prague, Czech Republic, pp 177–180Google Scholar
  19. Kumar S, Deng Y, Byrne W (2006) A weighted finite state transducer translation template model for statistical machine translation. Nat Lang Eng 12(1): 35–75CrossRefGoogle Scholar
  20. Li Z, Callison-Burch C, Dyer C, Ganitkevitch J, Khudanpur S, Schwartz L, Thornton WNG, Weese J, Zaidan OF (2009) Joshua: an open source toolkit for parsing-based machine translation. In: Procee- dings of the ACL Workshop on Statistical Machine Translation, Morristown, NJ, pp 135–139Google Scholar
  21. Llorens D, Vilar JM, Casacuberta F (2002) Finite state language models smoothed using n-grams. Int J Pattern Recognit Artif Intell 16(3): 275–289CrossRefGoogle Scholar
  22. Marcu D, Wong W (2002) A phrase-based, joint probability model for statistical machine translation. In: Proceedings of the 7th Conference on Empirical Methods in Natural Language Processing, Morristown, NJ, pp 133–139Google Scholar
  23. Mariño JB, Banchs RE, Crego JM, de Gispert A, Lambert P, Fonollosa JAR, Costa-jussà MR (2006) N-gram-based machine translation. Comput Linguist 32(4): 527–549MathSciNetCrossRefGoogle Scholar
  24. Medvedev YT (1964) On the class of events representable in a finite automaton. In: Moore EF (eds) Sequential machines selected papers. Addison Wesley, Reading, MAGoogle Scholar
  25. Mohri M, Pereira F, Riley M (2002) Weighted finite-state transducers in speech recognition. Comput Speech Lang 16(1): 69–88CrossRefGoogle Scholar
  26. Och FJ, Ney H (2002) Discriminative training and maximum entropy models for statistical machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, PA, pp 295–302Google Scholar
  27. Och FJ, Ney H (2003) A systematic comparison of various statistical alignment models. Comput Linguist 29(1): 19–51CrossRefGoogle Scholar
  28. Ortiz D, García-Varea I, Casacuberta F (2005) Thot: a toolkit to train phrase-based statistical translation models. In: Proceedings of the 10th Machine Translation Summit, Phuket, Thailand, pp 141–148Google Scholar
  29. Papineni K, Roukos S, Ward T, Zhu WJ (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, PA, pp 311–318Google Scholar
  30. Pérez A, Torres MI, Casacuberta F (2008) Joining linguistic and statistical methods for Spanish-to-Basque speech translation. Speech Commun 50: 1021–1033CrossRefGoogle Scholar
  31. Picó D, Casacuberta F (2001) Some statistical-estimation methods for stochastic finite-state transducers. Mach Learn 44: 121–142zbMATHCrossRefGoogle Scholar
  32. Rosenfeld R (1996) A maximum entropy approach to adaptive statistical language modeling. Comput Speech Lang 10: 187–228CrossRefGoogle Scholar
  33. Simard M, Plamondon P (1998) Bilingual sentence alignment: balancing robustness and accuracy. Mach Transl 13(1): 59–80CrossRefGoogle Scholar
  34. Singh AK, Husain S (2007) Exploring translation similarities for building a better sentence aligner. In: Proceedings of the 3rd Indian International Conference on Artificial Intelligence, Pune, India, pp 1852–1863Google Scholar
  35. Steinbiss V, Tran BH, Ney H (1994) Improvements in beam search. In: Proceedings of the 3rd International Conference on Spoken Language Processing, Yokohama, Japan, pp 2143–2146Google Scholar
  36. Torres MI, Varona A (2001) k-TSS language models in speech recognition systems. Comput Speech Lang 15(2): 127–149CrossRefGoogle Scholar
  37. Vidal E (1997) Finite-state speech-to-speech translation. In: Proceedings of the 22nd IEEE International Conference on Acoustic, Speech and Signal Processing, Munich, Germany, pp 111–114Google Scholar
  38. Vidal E, Thollard F, de la Higuera C, Casacuberta F, Carrasco RC (2005) Probabilistic finite-state machines–Part II. IEEE Trans Pattern Anal Mach Intell 27(7): 1025–1039Google Scholar
  39. Viterbi A (1967) Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Trans Inf Theory 13(2): 260–269zbMATHCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2011

Authors and Affiliations

  1. 1.Departamento de Sistemas Informáticos y Computación, Instituto Tecnológico de InformáticaUniversitat Politècnica de ValènciaValènciaSpain

Personalised recommendations