Machine Translation

, Volume 19, Issue 3–4, pp 301–323 | Cite as

Hybrid data-driven models of machine translation

Original Paper

Abstract

This paper presents an extended, harmonised account of our previous work on combining subsentential alignments from phrase-based statistical machine translation (SMT) and example-based MT (EBMT) systems to create novel hybrid data-driven systems capable of outperforming the baseline SMT and EBMT systems from which they were derived. In previous work, we demonstrated that while an EBMT system is capable of outperforming a phrase-based SMT (PBSMT) system constructed from freely available resources, a hybrid ‘example-based’ SMT system incorporating marker chunks and SMT subsentential alignments is capable of outperforming both baseline translation models for French–English translation. In this paper, we show that similar gains are to be had from constructing a hybrid ‘statistical’ EBMT system. Unlike the previous research, here we use the Europarl training and test sets, which are fast becoming the standard data in the field. On these data sets, while all hybrid ‘statistical’ EBMT variants still fall short of the quality achieved by the baseline PBSMT system, we show that adding the marker chunks to create a hybrid ‘example-based’ SMT system outperforms the two baseline systems from which it is derived. Furthermore, we provide further evidence in favour of hybrid systems by adding an SMT target-language model to the EBMT system, and demonstrate that this too has a positive effect on translation quality. We also show that many of the subsentential alignments derived from the Europarl corpus are created by either the PBSMT or the EBMT system, but not by both. In sum, therefore, despite the obvious convergence of the two paradigms, the crucial differences between SMT and EBMT contribute positively to the overall translation quality. The central thesis of this paper is that any researcher who continues to develop an MT system using either of these approaches will benefit further from integrating the advantages of the other model; dogged adherence to one approach will lead to inferior systems being developed.

Keywords

Hybrid Example-based MT Statistical MT Statistical language models Convergence Chunk coverage Europarl corpus 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Aue A, Menezes A, Moore R, Quirk C, Ringger E (2004) Statistical machine translation using labeled semantic dependency graphs. In: Proceedings of the tenth conference on theoretical and methodological issues in machine translation TMI-04, Baltimore, Maryland, pp. 125–134Google Scholar
  2. Bangalore S, Murdock V, Riccardi G (2002) Boostrapping bilingual data using consensus translation for a multilingual instant messaging system. In: Coling 2002 Proceedings of the 19th international conference on computational linguistics, Taipei, Taiwan, pp. 1–7Google Scholar
  3. Brown PF, Cocke J, Della Pietra SA, Della Pietra VJ, Jelinek F, Lafferty JD, Mercer RL, Roossin PS (1990) A statistical approach to machine translation. Comput Ling 16:79–85; repr. in Nirenburg, et al. pp. 355–362Google Scholar
  4. Brown PF, Della Pietra SA, Della Pietra VJ, Mercer RL (1993) The mathematics of statistical machine translation: Parameter estimation. Comput Ling 19:263–311Google Scholar
  5. Brown RD (1999) Adding linguistic knowledge to a lexical example-based translation system. In: Proceedings of the 8th international conference on theoretical and methodological issues in machine translation (TMI-99), Chester, England, pp. 22–32Google Scholar
  6. Callison-Burch C, Osborne M, Koehn P (2006) Re-evaluating the role of bleu in machine translation research. In: 11th conference of the European Association for Computational Linguistics, Trento, Italy, pp. 249–256Google Scholar
  7. Carl M, Hansen S (1999) Linking translation memories with example-based machine translation. In: Proceedings of MT Summit VII “MT in the great translation era”, Singapore, pp. 617–624Google Scholar
  8. Carl M, Way A (eds) (2003) Recent advances in example-based machine translation. Kluwer Academic Publishers, Dordrecht The NetherlandsGoogle Scholar
  9. Germann U, Jahr M, Knight K, Marcu D, Yamada K (2001) Fast decoding and optimal decoding for machine translation. In: Association for Computational Linguistics: 39th annual meeting and 10th conference of the European chapter, Toulouse, France, pp. 228–235Google Scholar
  10. Goodman J (2001) A bit of progress in language modeling. Comput Speech Lang 15:403–434CrossRefGoogle Scholar
  11. Gough N (2005) Example-based machine translation using the marker hypothesis. PhD Thesis, Dublin City University, Dublin, IrelandGoogle Scholar
  12. Gough N, Way A (2004a) Example-based controlled translation. In: Proceedings of the 9th EAMT workshop: Broadening horizons of machine translation and its applications, Valetta, Malta, pp. 73–81Google Scholar
  13. Gough N, Way A (2004b) Robust large-scale EBMT with marker-based segmentation. In: Proceedings of the tenth conference on theoretical and methodological issues in machine translation TMI-04, Baltimore, MD, pp. 95–104Google Scholar
  14. Green T (1979) The necessity of syntax markers: Two experiments with artificial languages. J Verb Learn Behav 18:481–496CrossRefGoogle Scholar
  15. Groves D, Way A (2005) Hybrid example-based SMT: The best of both worlds? In: Proceedings of the ACL 2005 workshop on building and using parallel texts: Data-driven machine translation and beyond, Ann Arbor, MI, pp. 183–190Google Scholar
  16. Hearne M, Way A (2003) Seeing the wood for the trees: Data-oriented translation. In: MT Summit IX: Proceedings of the ninth machine translation summit, New Orleans, USA, pp. 165–172Google Scholar
  17. Imamura K, Okuma H, Watanabe T, Sumita E (2004) Example-based machine translation based on syntactic transfer with statistical models. In: Coling: 20th international conference on computational linguistics, Geneva, Switzerland, pp. 99–105Google Scholar
  18. Koehn P (2004a) Statistical significance tests for machine translation evaluation. In: Conference on empirical methods in natural language processing, Barcelona, Spain, pp. 388–395Google Scholar
  19. Koehn P (2004b) Pharaoh: A beam search decoder for phrase-based statistical machine translation models. In: Frederking RE, Taylor KB (eds) Machine translation: From real users to research; 6th conference of the Association for Machine Translation in the Americas, AMTA 2004, Washington, DC, USA, September/October 2004, Springer, Berlin, Germany, pp. 115–124Google Scholar
  20. Koehn P (2005) Europarl: A parallel corpus for statistical machine translation. In: MT Summit X: The tenth machine translation summit, Phuket, Thailand, pp. 79–86Google Scholar
  21. Koehn P, Och FJ, Marcu D (2003) Statistical phrase-based translation. In: HLT-NAACL: Human language technology conference of the North American chapter of the Association for Computational Linguistics, Edmonton, Alberta, Canada, pp. 127–133Google Scholar
  22. Langlais P, Simard M (2002) Merging example-based and statistical machine translation. In: Richardson SD (ed) Machine translation: From research to real users, 5th conference of the Association for Machine Translation in the Americas (AMTA-2002), Tiburon, CA, USA, October 2002 proceedings, Springer, Berlin, Germany, pp. 104–113Google Scholar
  23. Marcu D (2001) Towards a unified approach to memory- and statistical-based machine translation. In: Association for Computational Linguistics: 39th annual meeting and 10th conference of the European chapter, Toulouse, France, pp. 378–385Google Scholar
  24. Marcus M, Kim G, Marcinkiewicz MA, MacIntyre R, Ferguson M, Katz K, Schasberger B (1994) The Penn Treebank: Annotating predicate argument structure. In: Proceedings of the ARPA human language technology workshop, Princeton, NJ, pp. 110–115Google Scholar
  25. Nagao M (1984) A framework of a mechanical translation between Japanese and English by analogy principle. In Elithorn A, Banerji R (eds) Artificial and human intelligence (Edited review papers presented at the international NATO symposium on artificial and human intelligence), North-Holland, Amsterdam, The Netherlands, 173–180; repr. in Nirenburg, et al. pp. 351–354Google Scholar
  26. Nirenburg S, Somers H, Wilks Y (eds) (2003) Readings in machine translation. MIT Press, Cambridge MAGoogle Scholar
  27. Och FJ (2003) Minimum error rate training in statistical machine translation. In: 41st annual meeting of the Association for Computational Linguistics, Sapporo, Japan, pp. 160–167Google Scholar
  28. Och FJ, Ney H (2003) A systematic comparison of various statistical alignment models. Comput Ling 29:19–51CrossRefGoogle Scholar
  29. Papineni K, Roukos S, Ward T, Zhu W-J (2002) Bleu: A method for automatic evaluation of machine translation. In: 40th annual meeting of the Association for Computational Linguistics, Philadelphia, Pennsylvania, pp. 311–318Google Scholar
  30. Paul M, Doi T, Hwang Y, Imamura K, Sumita E (2005a) Nobody is perfect: ATR’s hybrid approach to spoken language translation. In: Proceedings of the international workshop on spoken language translation (IWSLT 2005), Pittsburgh, PA, pp. 55–62Google Scholar
  31. Paul M, Sumita E, Yamamoto S (2005b) A machine learning approach to hypothesis selection of greedy decoding for SMT. In: MT Summit X workshop: Second workshop on example-based machine translation, Phuket, Thailand, pp. 117–124Google Scholar
  32. Planas E, Furuse O (2003) Formalizing translation memory. In Carl and Way (2003), pp. 157–188Google Scholar
  33. Quirk C, Menezes A (2006) Dependency treelet translation: The convergence of statistical and example-based machine-translation?. Mach Translat 20:45–66Google Scholar
  34. Turian JP, Shen L, Melamed ID (2003) Evaluation of machine translation and its evaluation. In: MT Summit IX: Proceedings of the ninth machine translation summit, New Orleans, USA, pp. 386–393Google Scholar
  35. Vogel S, Ney H (2000) Construction of a hierarchical translation memory. In: Proceedings of the 18th international conference on computational linguistics: COLING 2000 in Europe, Saarbrücken, Germany, pp. 1131–1135Google Scholar
  36. Watanabe H, Kurohashi S, Aramaki E (2003) Finding translation patterns from paired source and target dependency structures. In Carl and Way (2003), pp. 397–420Google Scholar
  37. Way A, Gough N (2003) wEBMT: developing and validating an example-based machine translation system using the World Wide Web. Comput Ling 29:421–457CrossRefGoogle Scholar
  38. Way A, Gough N (2005a) Comparing example-based and statistical machine translation. Nat Lang Eng 11:295–309CrossRefGoogle Scholar
  39. Way A, Gough N (2005b) Controlled translation in an example-based environment: What do automatic evaluation metrics tell us?. Mach Translat 19:1–36CrossRefGoogle Scholar
  40. Wu D (2006) MT model space: Statistical vs. compositional vs. example-based machine translation. Mach Translat 19:213–228Google Scholar

Copyright information

© Springer Science+Business Media 2006

Authors and Affiliations

  1. 1.School of ComputingDublin City UniversityDublin 9Ireland

Personalised recommendations