Skip to main content

Example-based machine translation: a review and commentary

Abstract

In the last decade the dominant models of MT have been data-driven or corpus-based. Of the two main trends, statistical machine translation and example-based machine translation (EBMT), the latter is much less clearly defined. In a review of the recently published collection edited by Michael Carl and Andy Way, this essay surveys the basic processes, methods, main problems and tasks of EBMT, and attempts to provide a definition of the essence of EBMT in comparison with statistical MT and traditional rule-based MT.

This is a preview of subscription content, access via your institution.

References

  • Brown P, Cocke J, Della Pietra S, Della Pietra V, Jelinek F, Mercer R, Roossin, P (1988) A statistical approach to French/English translation. In: Second international conference on theoretical and methodological issues in machine translation of natural languages, Pittsburgh, PA, 16 unnumbered pages

  • Brown PF, Della Pietra SA, Della Pietra VJ, Mercer RL (1993) The mathematics of statistical machine translation: parameter estimation. Comput Ling 19:263–311

    Google Scholar 

  • Brown R (2005) Context-sensitive retrieval for example-based translation. In: MT Summit X second workshop on example-based machine translation, Phuket, Thailand, pp 9–15

  • Charniak E, Knight K, Yamada K (2003) Syntax-based language models for statistical machine translation. In: MT Summit IX, proceedings of the ninth machine translation summit, New Orleans, LA, pp 40–46

  • Cicekli I (2005) Learning translation templates with type constraints. In: MT Summit X second workshop on example-based machine translation, Phuket, Thailand, pp 27–33 [Revised version titled ‘Inducing translation templates with type constraints’ in this issue]

  • Denoual E (2005) The influence of example-data homogeneity on EBMT quality. In: MT Summit X second workshop on example-based machine translation, Phuket, Thailand, pp 35–42

  • Doi T, Yamamoto H, Sumita E (2005) Graph-based retrieval for example-based machine translation using edit-distance. In: MT Summit X second workshop on example-based machine translation, Phuket, Thailand, pp 51–58

  • 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 73–81

  • 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, Maryland, pp 95–104

  • 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 183–190 [Extended revised version ‘Hybrid data-driven models of machine translation’ in this issue]

  • Hutchins J (2005) Towards a definition of example-based machine translation. In: MT Summit X second workshop on example-based machine translation, Phuket, Thailand, pp 63–70

  • Jones D (1992) Non-hybrid example-based machine translation architectures. In: TMI (1992), pp 163–171

  • Kaji H, Kida Y, Morimoto Y (1992) Learning translation templates from bilingual text. In: Coling-92: Proceedings of the fifteenth [sic] international conference on computational linguistics, Nantes, France, pp 672–678

  • Langlais P, Gotti F, Bourigault D, Coulombe C (2005) EBMT by tree-phrasing: a pilot study. In: MT Summit X second workshop on example-based machine translation, Phuket, Thailand, pp 71–80 [Revised version by Langlais and Gotti in this issue]

  • Lepage Y, Denoual, E (2005) The ‘purest’ EBMT system ever built: no variables, no templates, no training, examples, just examples, only examples. In: MT Summit X second workshop on example-based machine translation, Phuket, Thailand, pp 81–90 [Revised version in this issue]

  • Menezes A, Quirk C (2005) Dependency treelet translation: the convergence of statistical and example-based machine-translation? In: MT Summit X second workshop on example-based machine translation, Phuket, Thailand, pp 99–108 [Revised version by Quirk and Menezes in this issue]

  • 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. North- Holland, Amsterdam, pp 173–180

  • Richardson SD, Vanderwende L, Dolan W (1993) Combining dictionary-based and example-based methods for natural language analysis. In: Proceedings of the fifth international conference on theoretical and methodological issues in machine translation, TMI’93—MT in the next generation, Kyoto, Japan, pp 69–79

  • Saha D, Bandyopadhyay S (2005) A semantics-based English-Bengali EBMT system for translating news headlines. In: MT Summit X second workshop on example-based machine translation, Phuket, Thailand, pp 125–133

  • Somers H (1999) Review article: example-based machine translation. Mach Translat 14:113–157

    Article  Google Scholar 

  • Sumita E, Furuse O, Iida H (1993) An example-based disambiguation of prepositional phrase attachment. In: Proceedings of the fifth international conference on theoretical and methodological issues in machine translation, TMI ’93—MT in the next generation, Kyoto, Japan, pp 80–91

  • Sumita E, Iida H, Kohyama H (1990) Translating with examples: a new approach to machine translation. In: Third international conference on theoretical and methodological issues in machine translation, Austin, Texas, pp 203–212

  • TMI (1992) Fourth international conference on theoretical and methodological issues in machine translation (TMI-92), Montréal, Canada

  • Vandeghinste V, Dirix P, Schuurman I (2005) Example-based translation without parallel corpora: first experiment on a prototype. In: MT Summit X second workshop on example-based machine translation, Phuket, Thailand, pp 135–142

  • Watanabe H (1993) A method of extracting translation patterns from translation examples. In: Proceedings of the fifth international conference on theoretical and methodological issues in machine translation, TMI ’93—MT in the next generation, Kyoto, Japan pp 292–301

  • Way A, Gough N (2005a) Comparing example-based and statistical machine translation. Nat Lang Eng 11:295–309

    Article  Google Scholar 

  • Way A, Gough N (2005b) Controlled translation in an example-based environment: what do automatic evaluation metrics tell us? Mach Translat 19:1–36

    Article  Google Scholar 

  • Whitelock P (1994). Shake-and-bake translation. In: Rupp CJ, Rosner M, Johnson RL (eds). Constraints, language and computation. Academic Press, London, pp. 339–359

    Google Scholar 

  • Wu D (2006) MT model space: statistical vs. compositional vs. example-based machine translation. Mach Translat [this issue]

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to John Hutchins.

Additional information

Recent Advances in Example-based Machine Translation. Edited by Michael Carl and Andy Way. Dordrecht: Kluwer Academic Publishers, 2003. xxxi, 482pp. (Text, Speech and Language Technology, vol. 21) ISBN: 1-4020-1400-7 (hardback), 1-4020-1401-5 (paperback).

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Hutchins, J. Example-based machine translation: a review and commentary. Machine Translation 19, 197–211 (2005). https://doi.org/10.1007/s10590-006-9003-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10590-006-9003-9

Keywords