Statistical Machine Translation into a Morphologically Complex Language

  • Kemal Oflazer
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4919)

Abstract

In this paper, we present the results of our investigation into phrase-based statistical machine translation from English into Turkish – an agglutinative language with very productive inflectional and derivational word-formation processes. We investigate different representational granularities for morphological structure and find that (i) representing both Turkish and English at the morpheme-level but with some selective morpheme-grouping on the Turkish side of the training data, (ii) augmenting the training data with “sentences” comprising only the content words of the original training data to bias root word alignment, and with highly-reliable phrase-pairs from an earlier corpus-alignment (iii) re-ranking the n-best morpheme-sequence outputs of the decoder with a word-based language model, and (iv) “repairing” translated words with incorrect morphological structure and words which are out-of-vocabulary relative to the training and the language model corpus, provide an non-trivial improvement over a word-based baseline despite our very limited training data. We improve from 19.77 BLEU points for our word-based baseline model to 26.87 BLEU points for an improvement of 7.10 points or about 36% relative. We briefly discuss the applicability of BLEU to morphologically complex languages like Turkish and present a simple extension to compare tokens not in a all-or-none fashion but taking lexical-semantic and morpho-semantic similarities into account, implemented in our BLEU+ tool.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Durgar El-Kahlout, I., Oflazer, K.: Initial explorations in English to Turkish statistical machine translation. In: Proceedings on the Workshop on Statistical Machine Translation, pp. 7–14. Association for Computational Linguistics, New York City (2006)Google Scholar
  2. 2.
    Talbot, D., Osborne, M.: Modelling lexical redundancy for machine translation. In: Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Sydney, Australia, July 2006, pp. 969–976 (2006)Google Scholar
  3. 3.
    Oflazer, K., Durgar El-Kahlout, I.: Exploring different representational units in English-to-Turkish statistical machine translation. In: Proceedings of the Second Workshop on Statistical Machine Translation, pp. 25–32. Association for Computational Linguistics, Prague, Czech Republic (2007)Google Scholar
  4. 4.
    Niessen, S., Ney, H.: Statistical machine translation with scarce resources using morpho-syntatic information. Computational Linguistics 30, 181–204 (2004)CrossRefGoogle Scholar
  5. 5.
    Yang, M., Kirchhoff, K.: Phrase-based backoff models for machine translation of highly inflected languages. In: Proceedings of EACL, pp. 41–48 (2006)Google Scholar
  6. 6.
    Corston-Oliver, S., Gamon, M.: Normalizing German and English inflectional morphology to improve statistical word alignment. In: Proceedings of AMTA, pp. 48–57 (2004)Google Scholar
  7. 7.
    Lee, Y.-S.: Morphological analysis for statistical machine translation. In: Proceedings of HLT-NAACL 2004 - Companion Volume, pp. 57–60 (2004)Google Scholar
  8. 8.
    Zollmann, A., Venugopal, A., Vogel, S.: Bridging the inflection morphology gap for Arabic statistical machine translation. In: Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers, New York City, USA, pp. 201–204 (2006)Google Scholar
  9. 9.
    Popovic, M., Ney, H.: Towards the use of word stems and suffixes for statistical machine translation. In: Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC), pp. 1585–1588 (2004)Google Scholar
  10. 10.
    Goldwater, S., McClosky, D.: Improving statistical MT through morphological analysis. In: Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Vancouver, British Columbia, Canada, pp. 676–683 (2005)Google Scholar
  11. 11.
    Minkov, E., Toutanova, K., Suzuki, H.: Generating complex morphology for machine translation. In: Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pp. 128–135. Association for Computational Linguistics, Prague, Czech Republic (2007)Google Scholar
  12. 12.
    Oflazer, K.: Two-level description of Turkish morphology. Literary and Linguistic Computing 9, 137–148 (1994)CrossRefGoogle Scholar
  13. 13.
    Yüret, D., Türe, F.: Learning morphological disambiguation rules for Turkish. In: Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, New York City, USA, pp. 328–334 (2006)Google Scholar
  14. 14.
    Schmid, H.: Probabilistic part-of-speech tagging using decision trees. In: Proceedings of International Conference on New Methods in Language Processing (1994)Google Scholar
  15. 15.
    Koehn, P., Och, F.J., Marcu, D.: Statistical phrase-based translation. In: Proceedings of HLT/NAACL (2003)Google Scholar
  16. 16.
    Koehn, P., et al.: Moses: Open source toolkit for statistical machine translation. In: Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL 2007) – Companion Volume (2007)Google Scholar
  17. 17.
    Stolcke, A.: Srilm – an extensible language modeling toolkit. In: Proceedings of the Intl. Conf. on Spoken Language Processing (2002)Google Scholar
  18. 18.
    Papineni, K., et al.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, University of Pennsylvania, pp. 311–318 (2002)Google Scholar
  19. 19.
    Oflazer, K.: Error-tolerant finite-state recognition with applications to morphological analysis and spelling correction. Computational Linguistics 22, 73–90 (1996)Google Scholar
  20. 20.
    Zens, R., Ney, H.: N-gram posterior probabilities for statistical machine translation. In: Proceedings on the Workshop on Statistical Machine Translation, pp. 72–77. Association for Computational Linguistics, New York City (2006)Google Scholar
  21. 21.
    Tantuǧ, C., Oflazer, K., Durgar El-Kahlout, I.: BLEU+: a tool for fine-grained BLEU computation (Submitted, 2007)Google Scholar
  22. 22.
    Banerjee, S., Lavie, A.: METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, Ann Arbor, Michigan, pp. 65–72 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Kemal Oflazer
    • 1
  1. 1.Faculty of Engineering and Natural SciencesSabancı UniversityIstanbulTurkey

Personalised recommendations