Language Resources and Evaluation

, Volume 39, Issue 1, pp 91–108 | Cite as

Hybrid Architectures for Machine Translation Systems



Although some progress has been made on the quality of Machine Translation in recent years, there is still a significant potential for quality improvement. There has also been a shift in paradigm of machine translation, from “classical” rule-based systems like METAL or LMT1 towards example-based or statistical MT.2 It seems to be time now to evaluate the progress and compare the results of these efforts, and draw conclusions for further improvements of MT quality.

The paper starts with a comparison between statistical MT (henceforth: SMT) and rule-based MT (henceforth: RMT) systems, and describes the set-up and the evaluation results; the second section analyses the strengths and weaknesses of the respective approaches, and the third one discusses models of an architecture for a hybrid system.


evaluation architecture MT architecture Machine Translation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Amtrup J.W., Megerdoomian K., Zajac R. (2000) Rapid Development of Translation Tools: Application to Persian and Turkish. Proc. COLING.Google Scholar
  2. Atkins S., Bouillon P. (2002) The Lexicographic Approach: Sense Indicators as Candidates for Transfer Conditions. Proc. ISLE Workshop Pisa.Google Scholar
  3. Babych B., Hartley A. (2003) Improving Machine Translation Quality with Automatic Named Entity Recognition. Proc. EACL-EAMT, Budapest.Google Scholar
  4. Bel N., Busa F., Calzolari N., Gola E., Lenci A., Monacchini M., Ogonowski A., Peters I., Peters W., Ruimy N., Villegas M., Zampolli A. (2000) SIMPLE: A General Framework for the Development of Multilingual Lexicons. Proc. LREC 2000, Athens.Google Scholar
  5. Bernardi U., Gieselmann P., McLaughlin St. (2001) A Taste of MALT. Proc. MT Summit, Santiago di Compostella.Google Scholar
  6. Buschbeck B., Henschel R., Höser I., Klimonow G., Küstner A., Starke I. (1990) VIRTEX – a German–Russian Translation Experiment. Proceedings of COLING-90, Helsinki.Google Scholar
  7. Calzolari N., Bertagna F., Lenci A., Monachini M. (ed) (2002a) Standards and best practice for multilingual computational Lexicons and MILE (the Multilingual ISLE Lexical Entry). ISLE-Report 2002.Google Scholar
  8. Calzolari N. Grishman R., Palmer M. (2002b). Standards & Best Practice for Multilingual computational lexicons: ISLE MILE and More. Proc. LREC 2002, Gran Canaria.Google Scholar
  9. Chomsky N. (1957) Syntactic Structures. The Hague.Google Scholar
  10. Coughlin D. (2003) Correlating Automated and Human Assessments of Machine Translation Quality. Proc. Machine Translation Summit IX, New Orleans.Google Scholar
  11. Grishman R., Sterling J. (1992) Acquisition of Selectional Patterns. Proc 14th COLING, Nantes.Google Scholar
  12. Hovy, E., King, M., Popescu-Belis, A. 2002Principles of Context-Based Machine Translation EvaluationMachine Translation171951CrossRefGoogle Scholar
  13. Jablonski, K., Rau, A., Ritzke, J. 1990Wissensbasierte TextgenerierungTübingenNarrGoogle Scholar
  14. King M., Popescu-Belis A., Hovy E. (2003) FEMTI: Creating and using a Framework for MT Evaluation, Proc. Machine Translation Summit IX, New Orleans.Google Scholar
  15. Knight K., Koehn Ph. (2003) Introduction to Statistical Machine Translation. Tutorial MT Summitt 2003, New Orleans.Google Scholar
  16. McCord M. (1989) A New Version of the Machine Translation System LMT. Lit. and Ling. Computing 4.Google Scholar
  17. Menezes A., Richardson St. (2001) A Best-First Alignment Algorithm for Automatic Extraction of Transfer Mappings from Bilingual Corpora. Proc. MT Summit VIII, Santiago, Workshop on Example-based Machine Translation.Google Scholar
  18. (NIST, 2001) Automatic Evaluation of Machine Translation Quality Using N-gram Co-Occurrence Statistics. Scholar
  19. Nießen S., Ney H. (2000) Improving SMT Quality with Morpho-Syntactic Analysis. Proc. COLING.Google Scholar
  20. Och F., Gildea D., Khudanpur S., et al. (2003) Syntax for Statistical Machine Translation. John Hopkins Summer Workshop. Scholar
  21. Och F., Ney H. (2001) Statistical Multi-Source Translation. Proc. MT Summit VIII, Santiago.Google Scholar
  22. Och, F.J., Ney, H. 2003A Systematic Comparison of Various Statistical Alignment ModelsComputational Linguistics291951CrossRefGoogle Scholar
  23. Papieni K., Roukos S., Ward T., Zhu W.-J. (2002) BLEU: A Method for Automatic Evaluation of Machine Translation. Proc. 40th ACL, Philadelphia.Google Scholar
  24. Piperidis St., Boutsis S., Demiros J. (1997) Automatic Translation Lexicon Generation from Multilingual texts. Proc. AAAI 1997.Google Scholar
  25. Richardson St., Dolan W., Menezes A., Pinkham J. (2001) Achieving Commercial-Quality Translation with Example-Based Methods. Proc MT Summit Santiago di Compostela.Google Scholar
  26. Samiotou A., Kranias L., Papadopoulos G., Asunmaa M., Magnusdottir G. (2004) Exploitation of parallel texts for Populating MT & TM Databases. Proc. LREC, Workshop on The Amazing Utilty of Parallel and Comparable Corpora, Lisbon.Google Scholar
  27. Steiner E., Winter-Thielen J. (1988) On The Semantics of Focus Phenomena in EUROTRA. Proc. COLING, Budapest.Google Scholar
  28. Thurmair Gr. (1990) METAL: Computer Integrated Translation. Proc. Workshop on Machine Translation, UMIST Manchester.Google Scholar
  29. Thurmair G. (2000) TQPro, Quality Tools for the translation process. Proc. ASLIB, London.Google Scholar
  30. Thurmair G. (2003) Making Term Extraction Tools Usable. Proc EAMT-CLAW Dublin.Google Scholar
  31. Vanni M., Voss C.R., Tate C. (2004) Ground Truth, Referent Truth and “Omniscient” Truth – Parallel Phrases in Parallel Texts for MT Evaluation. Proc. LREC, Workshop on The Amazing Utilty of Parallel and Comparable Corpora, Lisbon.Google Scholar
  32. Vogel S., Och F, Ney H. (2000) The Statistical translation Module in the Verbmobil System. Proc. KONVENS Ilmenau.Google Scholar
  33. Vogel, S., Och, F., Tillmann, Chr., Nießen, S., Sawaf, H., Ney, H. 2000Statistical Methods for Machine TranslationWahlster, W. eds. Verbmobil: Foundations of Speech-to-Speech TranslationSpringerBerlinGoogle Scholar
  34. Weber N. (2003) MÜ-Lexikografie. Proc. GLDV, Köthen.Google Scholar
  35. Whitelock P. (1992) Shake-and-bake Translation. Proc. COLING Nantes.Google Scholar

Copyright information

© Springer 2005

Authors and Affiliations

  1. 1.linguatic GmbHMunichGermany

Personalised recommendations