Abstract
In a statistical machine translation system (SMTS), decoding is the process of finding the most likely translation based on a statistical model according to previously learned parameters. This paper proposes a new approach based on evolutionary hybrid algorithms to translate sentences in a specific technical context. The tests are carried out in the context of Spanish and then translated to English. The experimental results validate the performance of our method.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This research was supported by Fondecyt Project 1040364
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Arnold, D., Balkan, L., Meier, S., Humphreys, R.L., Sadler, L.: Machine Translation: an Introductory Guide. Essex University (1995)
Chen, S.F., Goodman, J.T.: An empirical study of smoothing techniques for language modeling. In: 34th Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 3–25 (1996)
Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical Society 39(1), 1–38 (1977)
Ney, H., Och, F.: Statistical machine translation. In: EAMT Workshop, pp. 39–46 (2000)
Germann, U.: Greedy decoding for statistical machine translation in almost linear. In: Proceedings HLT-NAACL, pp. 72–79 (2003)
Hart, W., Belew, R.: Optimization with genetic algorithms hybrids that use local search. Addison Wesley, Reading (1996)
Knight, K.: Decoding complexity in word-replacement translation models. Computational Linguistics 25(4) (1999)
Germann, U., Jahr, M., Knight, K., Marcu, D., Yamada, K.: Fast decoding and optimal decoding for machine translation. In: Proceedings of ACL (2001)
Michalewicz, Z.: Genetics Algorithms + Data Structures = Evolution Programs. WNT, Warsaw (1996)
Josef Och, F., Ueffing, N., Ney, H.: Conference on empirical methods for natural language processing. IBM Journal Reseach and Development, 156–163 (2002)
Della Pietra, V., Brown, P., Della Pietra, S., Mercer, R.: The mathematics of statistical machine translation: Parameter estimation. Computational Linguistics 19(2), 263–312 (1993)
Riff, M., Bonnaire, X.: Inheriting parents operators: A new dynamic strategy for improving evolutionary algorithms. In: 13th International Symposium on Methodologies for Intelligent Systems, pp. 333–341 (2002)
Tillmann, C., Vogel, S., Ney, H., Sawaf, H., Zubiaga, A.: Accelerated dp-based search for statistical translation. In: 5th European Conference on Speech Communication and Technology, vol. 5, pp. 2667–2670 (1997)
Ney, H., Vogel, S., Tillman, C.: Hmm-based word alignment in statistical translation. In: 16th Int. Conf. On Computational Linguistics, vol. 16, pp. 836–841 (1999)
Watanabe, T., Sumita, E.: Bidirectional decoding for statistical machine translation. In: 19th Int. Conf. On Computational Linguistics, pp.1079–1085 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Otto, E., Riff, M.C. (2004). Towards an Efficient Evolutionary Decoding Algorithm for Statistical Machine Translation. In: Monroy, R., Arroyo-Figueroa, G., Sucar, L.E., Sossa, H. (eds) MICAI 2004: Advances in Artificial Intelligence. MICAI 2004. Lecture Notes in Computer Science(), vol 2972. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24694-7_45
Download citation
DOI: https://doi.org/10.1007/978-3-540-24694-7_45
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21459-5
Online ISBN: 978-3-540-24694-7
eBook Packages: Springer Book Archive