A Machine-Learning Framework for Hybrid Machine Translation

  • Christian Federmann
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7526)

Abstract

We present a Machine-Learning-based framework for hybrid Machine Translation. Our approach combines translation output from several black-box source systems. We define an extensible, total order on translation output and use this to decompose the n-best translations into pairwise system comparisons. Using joint, binarised feature vectors we train an SVM-based classifier and show how its classification output can be used to generate hybrid translations on the sentence level. Evaluations using automated metrics shows promising results. An interesting finding in our experiments is the fact that our approach allows to leverage good translations from otherwise bad systems as the combination decision is taken on the sentence instead of the corpus level. We conclude by summarising our findings and by giving an outlook to future work, e.g., on probabilistic classification or the integration of manual judgements.

Keywords

Hybrid Machine Translation System Combination Machine Learning Support Vector Machines Feature-Based Classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Avramidis, E.: DFKI System Combination with Sentence Ranking at ML4HMT-2011. In: Proceedings of the International Workshop on Using Linguistic Information for Hybrid Machine Translation (LIHMT 2011) and of the Shared Task on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid Machine Translation (ML4HMT). META-NET, Barcelona (2011)Google Scholar
  2. 2.
    Barrault, L.: Many: Open source machine translation system combination. Prague Bulletin of Mathematical Linguistics, Special Issue on Open Source Tools for Machine Translation 1(93), 145–155 (2010), http://www-lium.univ-lemans.fr/sites/default/files/Barrault-MANY2010.pdf Google Scholar
  3. 3.
    Chang, C.C., Lin, C.J.: LIBSVM: A Library for Support Vector Machines. ACM Transactions on Intelligent Systems and Technology 2, 27:1–27:27 (2011), Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
  4. 4.
    Chen, Y., Eisele, A., Federmann, C., Hasler, E., Jellinghaus, M., Theison, S.: Multi-engine machine translation with an open-source SMT decoder. In: Proceedings of the Second Workshop on Statistical Machine Translation, pp. 193–196. Association for Computational Linguistics, Prague (2007), http://www.aclweb.org/anthology/W/W07/W07-0726 CrossRefGoogle Scholar
  5. 5.
    Denkowski, M., Lavie, A.: Meteor 1.3: Automatic Metric for Reliable Optimization and Evaluation of Machine Translation Systems. In: Proceedings of the Sixth Workshop on Statistical Machine Translation, pp. 85–91. Association for Computational Linguistics, Edinburgh (2011), http://www.aclweb.org/anthology-new/W/W11/W11-2107 Google Scholar
  6. 6.
    Doddington, G.: Automatic Evaluation of Machine Translation Quality Using n-gram Co-occurrence Statistics. In: Proceedings of the Second International Conference on Human Language Technology Research, HLT 2002, pp. 138–145. Morgan Kaufmann Publishers Inc., San Francisco (2002), http://www.itl.nist.gov/iad/mig/tests/mt/doc/ngram-study.pdf CrossRefGoogle Scholar
  7. 7.
    Eisele, A., Federmann, C., Saint-Amand, H., Jellinghaus, M., Herrmann, T., Chen, Y.: Using Moses to integrate multiple rule-based machine translation engines into a hybrid system. In: Proceedings of the Third Workshop on Statistical Machine Translation, pp. 179–182. Association for Computational Linguistics, Columbus (2008), http://www.aclweb.org/anthology/W/W08/W08-0328 CrossRefGoogle Scholar
  8. 8.
    Frederking, R., Nirenburg, S.: Three Heads are Better Than One. In: Proceedings of the Fourth Conference on Applied Natural Language Processing, ANLC 1994, pp. 95–100. Association for Computational Linguistics, Stroudsburg (1994), http://ww2.cs.mu.oz.au/acl/A/A94/A94-1016.pdf CrossRefGoogle Scholar
  9. 9.
    Gamon, M., Aue, A., Smets, M.: Sentence-level MT Evaluation Without Reference Translations: Beyond Language Modeling. In: Proceedings of the 10th EAMT Conference ”Practical Applications of Machine Translation”, pp. 103–111. European Association for Machine Translation (May 2005), http://research.microsoft.com/research/pubs/view.aspx?pubid=1426
  10. 10.
    Green, S., Manning, C.D.: Better Arabic Parsing: Baselines, Evaluations, and Analysis. In: Proceedings of the 23rd International Conference on Computational Linguistics, COLING 2010, pp. 394–402. Association for Computational Linguistics, Stroudsburg (2010), http://dl.acm.org/citation.cfm?id=1873826 Google Scholar
  11. 11.
    He, Y., Ma, Y., van Genabith, J., Way, A.: Bridging SMT and TM with Translation Recommendation. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010, pp. 622–630. Association for Computational Linguistics, Stroudsburg (2010), http://aclweb.org/anthology-new/P/P10/P10-1064.pdf Google Scholar
  12. 12.
    He, Y., Ma, Y., Way, A., van Genabith, J.: Integrating N-best SMT Outputs into a TM System. In: Proceedings of the 23rd International Conference on Computational Linguistics, COLING 2010, pp. 374–382. Association for Computational Linguistics, Stroudsburg (2010), http://doras.dcu.ie/15799/1/Integrating_N-best_SMT_Outputs_into_a_TM_System.pdf
  13. 13.
    Klein, D., Manning, C.: Accurate Unlexicalized Parsing. In: Proceedings of the 41st Meeting of the Association for Computational Linguistics, ACL 2003, vol. 1, pp. 423–430. Association for Computational Linguistics, Stroudsburg (2003), http://acl.ldc.upenn.edu/P/P03/P03-1054.pdf
  14. 14.
    Levy, R., Manning, C.: Is it harder to parse Chinese, or the Chinese Treebank? In: Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, ACL 2003, pp. 439–446. Association for Computational Linguistics, Stroudsburg (2003), http://www.aclweb.org/anthology/P03-1056
  15. 15.
    Macherey, W., Och, F.J.: An Empirical Study on Computing Consensus Translations from Multiple Machine Translation Systems. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 986–995. Association for Computational Linguistics, Prague (2007), http://www.aclweb.org/anthology/D/D07/D07-1105 Google Scholar
  16. 16.
    Matusov, E., Ueffing, N., Ney, H.: Computing Consensus Translation from Multiple Machine Translation Systems Using Enhanced Hypotheses Alignment. In: Conference of the European Chapter of the Association for Computational Linguistics, pp. 33–40. Association for Computational Linguistics, Stroudsburg (2006), http://acl.ldc.upenn.edu/E/E06/E06-1005.pdf Google Scholar
  17. 17.
    Och, F.J., Ney, H.: A Systematic Comparison of Various Statistical Alignment Models. Computational Linguistics 29(1), 19–51 (2003), http://acl.ldc.upenn.edu/J/J03/J03-1002.pdf MATHCrossRefGoogle Scholar
  18. 18.
    Okita, T., van Genabith, J.: DCU Confusion Network-based System Combination for ML4HMT. In: Proceedings of the International Workshop on Using Linguistic Information for Hybrid Machine Translation (LIHMT 2011) and of the Shared Task on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid Machine Translation (ML4HMT). META-NET, Barcelona (2011)Google Scholar
  19. 19.
    Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: A Method for Automatic Evaluation of Machine Translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, ACL 2002, pp. 311–318. Association for Computational Linguistics, Stroudsburg (2002), http://acl.ldc.upenn.edu/P/P02/P02-1040.pdf Google Scholar
  20. 20.
    Rosti, A.V., Ayan, N.F., Xiang, B., Matsoukas, S., Schwartz, R., Dorr, B.: Combining Outputs from Multiple Machine Translation Systems. In: Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference, pp. 228–235. Association for Computational Linguistics, Rochester (2007), http://www.aclweb.org/anthology/N/N07/N07-1029 Google Scholar
  21. 21.
    Stolcke, A.: SRILM - An Extensible Language Modeling Toolkit. In: Proceedings of the International Conference on Spoken Language Processing, pp. 257–286 (November 2002)Google Scholar
  22. 22.
    Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer-Verlag New York, Inc., New York (1995)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Christian Federmann
    • 1
  1. 1.Language Technology LabGerman Research Center for Artificial IntelligenceSaarbrückenGermany

Personalised recommendations