Advertisement

Disambiguating Word Translations with Target Language Models

  • André Lynum
  • Erwin Marsi
  • Lars Bungum
  • Björn Gambäck
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7499)

Abstract

Word Translation Disambiguation is the task of selecting the best translation(s) for a source word in a certain context, given a set of translation candidates. Most approaches to this problem rely on large word-aligned parallel corpora, resources that are scarce and expensive to build. In contrast, the method presented in this paper requires only large monolingual corpora to build vector space models encoding sentence-level contexts of translation candidates as feature vectors in high-dimensional word space. Experimental evaluation shows positive contributions of the models to overall quality in German-English translation.

Keywords

word translation disambiguation vector space models 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Tambouratzis, G., Sofianopoulos, S., Vassiliou, M., Simistira, F., Tsimboukakis, N.: A resource-light phrase scheme for language-portable MT. In: Forcada, M.L., Depraetere, H., Vandeghinste, V. (eds.) Proceedings of the 15th Conference of the European Association for Machine Translation, Leuven, Belgium, pp. 185–192 (2011)Google Scholar
  2. 2.
    Salton, G.: Automatic Text Processing: The Transformation, Analysis and Retrieval of Information by Computer. Addison-Wesley, Reading (1989)Google Scholar
  3. 3.
    Carpuat, M., Wu, D.: Improving statistical machine translation using word sense disambiguation. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 61–72. ACL, Prague (2007)Google Scholar
  4. 4.
    van Gompel, M.: UvT-WSD1: A cross-lingual word sense disambiguation system. In: Proceedings of the 5th International Workshop on Semantic Evaluation, pp. 238–241. ACL (2010)Google Scholar
  5. 5.
    Vilariño Ayala, D., Balderas Posada, C., Pinto Avendaño, D.E., Rodríguez Hernández, M., León Silverio, S.: FCC: Modeling probabilities with GIZA++ for Task 2 and 3 of SemEval-2. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, 5th International Workshop on Semantic Evaluation, pp. 112–116. ACL, Uppsala (2010)Google Scholar
  6. 6.
    Silberer, C., Ponzetto, S.P.: UHD: Cross-lingual word sense disambiguation using multilingual co-occurrence graphs. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, 5th International Workshop on Semantic Evaluation, pp. 134–137. ACL, Uppsala (2010)Google Scholar
  7. 7.
    Koehn, P., Knight, K.: Estimating word translation probabilities from unrelated monolingual corpora using the em algorithm. In: National Conference on Artificial Intelligence (AAAI 2000), Langkilde, pp. 711–715 (2000)Google Scholar
  8. 8.
    Koehn, P., Knight, K.: Knowledge sources for word-level translation models. In: Lee, L., Harman, D. (eds.) Proceedings of the 2001 Conference on Empirical Methods in Natural Language Processing, pp. 27–35. ACL, Pittsburgh (2001)Google Scholar
  9. 9.
    Monz, C., Dorr, B.J.: Iterative translation disambiguation for cross-language information retrieval. In: Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2005, pp. 520–527. ACM, New York (2005)CrossRefGoogle Scholar
  10. 10.
    Rapp, R.: Automatic identification of word translations from unrelated english and german corpora. In: Proceedings of the 37thAnnual Meeting of the Association for Computational Linguistics, ACL 1999, pp. 519–526. ACL, College Park (1999)Google Scholar
  11. 11.
    Pomikálek, J., Rychlỳ, P., Kilgarriff, A.: Scaling to billion-plus word corpora. Advances in Computational Linguistics 41, 3–13 (2009)Google Scholar
  12. 12.
    Schmid, H.: Probabilistic part-of-speech tagging using decision trees. In: Proceedings of International Conference on New Methods in Language Processing, Manchester, UK, vol. 12, pp. 44–49 (1994)Google Scholar
  13. 13.
    Rychlý, P.: Manatee/Bonito – a modular corpus manager. In: 1st Workshop on Recent Advances in Slavonic Natural Language Processing, Brno, Masaryk University, pp. 65–70 (2007)Google Scholar
  14. 14.
    Marsi, E., Lynum, A., Bungum, L., Gambäck, B.: Word translation disambiguation without parallel texts. In: International Workshop on Using Linguistic Information for Hybrid Machine Translation (LIHMT 2011), Barcelona, Spain, pp. 66–74 (2011)Google Scholar
  15. 15.
    Weber, R., Schek, H.J., Blott, S.: A quantitative analysis and performance study for similarity-search methods in high-dimensional spaces. In: Gupta, A., Shmueli, O., Widom, J. (eds.) Proceedings of 24rd International Conference on Very Large Data Bases, VLDB 1998, August 24-27, pp. 194–205. Morgan Kaufmann, New York City (1998)Google Scholar
  16. 16.
    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, pp. 138–145. Morgan Kaufmann Publishers Inc. (2002)Google Scholar
  17. 17.
    Papineni, K., Roukos, S., Ward, T., Zhu, W.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL, pp. 311–318 (2002)Google Scholar
  18. 18.
    Cohen, T., Schvaneveldt, R., Widdows, D.: Reflective random indexing and indirect inference: A scalable method for discovery of implicit connections. Journal of Biomedical Informatics 43(2), 240–256 (2010)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • André Lynum
    • 1
  • Erwin Marsi
    • 1
  • Lars Bungum
    • 1
  • Björn Gambäck
    • 1
  1. 1.Department of Computer and Information ScienceNorwegian University of Science and Technology (NTNU)TrondheimNorway

Personalised recommendations