Advertisement

Domain Adaptation in Statistical Machine Translation Using Comparable Corpora: Case Study for English Latvian IT Localisation

  • Mārcis Pinnis
  • Inguna Skadiņa
  • Andrejs Vasiļjevs
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7817)

Abstract

In the recent years, statistical machine translation (SMT) has received much attention from language technology researchers and it is more and more applied not only to widely used language pairs, but also to under-resourced languages. However, under-resourced languages and narrow domains face the problem of insufficient parallel data for building SMT systems of reasonable quality for practical applications. In this paper we show how broad domain SMT systems can be successfully tailored to narrow domains using data extracted from strongly comparable corpora. We describe our experiments on adaptation of a baseline English-Latvian SMT system trained on publicly available parallel data (mostly legal texts) to the information technology domain by adding data extracted from in-domain comparable corpora. In addition to comparative human evaluation the adapted SMT system was also evaluated in a real life localisation scenario. Application of comparable corpora provides significant improvements increasing human translation productivity by 13.6% while maintaining an acceptable quality of translation.

Keywords

comparable corpus statistical machine translation software localisation under-resourced languages Latvian narrow domain 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Abdul-Rauf, S., Schwenk, H.: On the use of comparable corpora to improve SMT performance. In: Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics, Athens, Greece, pp. 16–23 (2009)Google Scholar
  2. 2.
    Abdul-Rauf, S., Schwenk, H.: Parallel sentence generation from comparable corpora for improved SMT. Machine Translation 25(4), 341–375 (2011)CrossRefGoogle Scholar
  3. 3.
    Bertoldi, N., Haddow, B., Fouet, J.B.: Improved Minimum Error Rate Training in Moses. The Prague Bulletin of Mathematical Linguistics 91, 7–16 (2009)CrossRefGoogle Scholar
  4. 4.
    Flournoy, R., Duran, C.: Machine translation and document localization at Adobe: From pilot to production. In: MT Summit XII: Proceedings of the Twelfth Machine Translation Summit, Ottawa, Canada (2009)Google Scholar
  5. 5.
    Hewavitharana, S., Vogel, S.: Enhancing a Statistical Machine Translation System by using an Automatically Extracted Parallel Corpus from Comparable Sources. In: Proceedings of the Workshop on Comparable Corpora, LREC 2008, pp. 7–10 (2008)Google Scholar
  6. 6.
    Koehn, P.: Statistical Machine Translation. Cambridge University Press (2010)Google Scholar
  7. 7.
    Koehn, P., Federico, M., Cowan, B., Zens, R., Duer, C., Bojar, O., Constantin, A., Herbst, E.: Moses: Open Source Toolkit for Statistical Machine Translation. In: Proceedings of the ACL 2007 Demo and Poster Sessions, Prague, pp. 177–180 (2007)Google Scholar
  8. 8.
    Lu, B., Jiang, T., Chow, K., Tsou, B.K.: Building a large English-Chinese parallel corpus from comparable patents and its experimental application to SMT. In: Proceedings of the 3rd Workshop on Building and using Comparable Corpora: from Parallel to Non-Parallel Corpora, Valletta, Malta, pp. 42–48 (2010)Google Scholar
  9. 9.
    Munteanu, D., Marcu, D.: Extracting parallel sub-sentential fragments from nonparallel corpora. In: Proceedings of the 21st International Conference on Computational Linguistics and the 44th Annual Meeting of the Association for Computational Linguistics, Morristown, NJ, USA, pp. 81–88 (2006)Google Scholar
  10. 10.
    Munteanu, D., Marcu, D.: Improving Machine Translation Performance by Exploiting Non-Parallel Corpora. Computational Linguistics 31(4), 477–504 (2006)CrossRefGoogle Scholar
  11. 11.
    O´Brien, S.: Methodologies for measuring the correlations between post-editing effort and machine translatability. Machine Translation 19(1), 37–58 (2005)CrossRefGoogle Scholar
  12. 12.
    Pinnis, M., Ion, R., Ştefănescu, D., Su, F., Skadiņa, I., Vasiļjevs, A., Babych, B.: ACCURAT Toolkit for Multi-Level Alignment and Information Extraction from Comparable Corpora. In: Proceedings of System Demonstrations Track of ACL 2012, Jeju Island, Republic of Korea (2012)Google Scholar
  13. 13.
    Pinnis, M., Ljubešić, N., Ştefănescu, D., Skadiņa, I., Tadić, M., Gornostay, T.: Term Extraction, Tagging and Mapping Tools for Under-Resourced Languages. In: Proceedings of the 10th Conference on Terminology and Knowledge Engineering, Madrid, Spain (2012)Google Scholar
  14. 14.
    Pinnis, M., Skadiņš, R.: MT Adaptation for Under-Resourced Domains – What Works and What Not. In: Proceedings of the Fifth International Conference Baltic HLT 2012, pp. 176–184. IOS Press, Tartu (2012)Google Scholar
  15. 15.
    Plitt, M., Masselot, F.: A Productivity Test of Statistical Machine Translation Post-Editing in a Typical Localisation Context. The Prague Bulletin of Mathematical Linguistics 93, 7–16 (2010)CrossRefGoogle Scholar
  16. 16.
    Schmidtke, D.: Microsoft office localization: use of language and translation technology (2008), http://www.tm-europe.org/files/resources/TM-Europe2008-Dag-Schmidtke-Microsoft.pdf
  17. 17.
    Skadiņa, I., Aker, A., Mastropavlos, N., Su, F., Tufiş, D., Verlič, M., Vasiļjevs, A., Babych, B., Clough, P., Gaizauskas, R., Glaros, N., Paramita, M.L., Pinnis, M.: Collecting and Using Comparable Corpora for Statistical Machine Translation. In: Proceedings of LREC 2012, Istanbul, Turkey, May 21-27, pp. 438–445 (2012)Google Scholar
  18. 18.
    Skadiņš, R., Goba, K., Šics, V.: Improving SMT for Baltic Languages with Factored Models. In: Proceedings of the Fourth International Conference Baltic HLT 2010, Riga, Latvia, October 7-8, pp. 125–132 (2010)Google Scholar
  19. 19.
    Skadiņš, R., Puriņš, M., Skadiņa, I., Vasiļjevs, A.: Evaluation of SMT in localization to under-resourced inflected language. In: Proceedings of the 15th International Conference of the European Association for Machine Translation EAMT 2011, Leuven, Belgium, May 30-31, pp. 35–40 (2011)Google Scholar
  20. 20.
    Su, F., Babych, B.: Measuring Comparability of Documents in Non-Parallel Corpora for Efficient Extraction of (Semi-) Parallel Translation Equivalents. In: Proceedings of the EACL 2012 Joint Workshop on Exploiting Synergies between Information Retrieval and Machine Translation (ESIRMT) and Hybrid Approaches to Machine Translation (HyTra), Avignon, France, April 23-27, pp. 10–19 (2012)Google Scholar
  21. 21.
    Steinberger, R., Eisele, A., Klocek, S., Pilos, S., Schlüter, P.: DGT-TM: A freely Available Translation Memory in 22 Languages. In: Proceedings of LREC 2012, Istanbul, Turkey, pp. 454–459 (2012)Google Scholar
  22. 22.
    Steinberger, R., Pouliquen, B., Widiger, A., Ignat, C., Erjavec, T., Tufis, D., Varga, D.: The JRC-Acquis: A multilingual aligned parallel corpus with 20+ languages. In: Proceedings of LREC 2006, Genoa, Italy, pp. 2142–2147 (2006)Google Scholar
  23. 23.
    Ştefănescu, D., Ion, R., Hunsicker, S.: Hybrid Parallel Sentence Mining from Comparable Corpora. In: Proceedings of the 16th Conference of the European Association for Machine Translation (EAMT 2012), Trento, Italy, May 28-30, pp. 137–144 (2012)Google Scholar
  24. 24.
    Tiedemann, J.: News from OPUS - A Collection of Multilingual Parallel Corpora with Tools and Interfaces. In: Recent Advances in Natural Language Processing, vol. V, pp. 237–248 (2009)Google Scholar
  25. 25.
    Vasiļjevs, A., Skadiņš, R., Tiedemann, J.: LetsMT!: a cloud-based platform for do-it-yourself machine translation. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (ACL 2012), Jeju, Republic of Korea, July 10. System Demonstrations, pp. 43–48 (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Mārcis Pinnis
    • 1
  • Inguna Skadiņa
    • 1
  • Andrejs Vasiļjevs
    • 1
  1. 1.TildeLatvia

Personalised recommendations