Abstract
We study the application of minimum description length (MDL) inference to estimate pattern recognition models for machine translation. MDL is a theoretically-sound approach whose empirical results are however below those of the state-of-the-art pipeline of training heuristics. We identify potential limitations of current MDL procedures and provide a practical approach to overcome them. Empirical results support the soundness of the proposed approach.
J. González-Rubio—This author is now at Unbabel Lda. 1000-201 Lisboa, Portugal.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
We have 8 different symbols: one symbol for each of the six words, plus \({{\mathrm{\bullet }}}\) and \({{\mathrm{\vert }}}\).
- 2.
14 is the maximum phrase pair length usually considered by conventional PB systems.
References
Koehn, P., Och, F.J., Marcu, D.: Statistical phrase-based translation. In: Proceedings of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, pp. 48–54 (2003)
Koehn, P., Hoang, H., Birch, A., Callison-Burch, C., Federico, M., Bertoldi, N., Cowan, B., Shen, W., Moran, C., Zens, R., Dyer, C., Bojar, O., Constantin, A., Herbst, E.: Moses: open source toolkit for statistical machine translation. In: Proceedings of the Association for Computational Linguistics, Demonstration Session (2007)
Sanchis-Trilles, G., Ortiz-Martínez, D., González-Rubio, J., González, J., Casacuberta, F.: Bilingual segmentation for phrasetable pruning in statistical machine translation. In: Proceedings of the Conference of the European Association for Machine Translation (2011)
Rissanen, J.: Modeling by shortest data description. Automatica 14(5), 465–471 (1978)
González-Rubio, J., Casacuberta, F.: Inference of phrase-based translation models via minimum description length. In: Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics, pp. 90–94 (2014)
Marcu, D., Wong, W.: A phrase-based, joint probability model for statistical machine translation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 133–139 (2002)
DeNero, J., Bouchard-Côté, A., Klein, D.: Sampling alignment structure under a bayesian translation model. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 314–323 (2008)
Zhang, J.: Model-based search for statistical machine translation. Master’s thesis, Edinburgh University, United Kingdom (2005)
Vilar, J.M., Vidal, E.: A recursive statistical translation model. In: Proceedings of the ACL Workshop on Building and Using Parallel Texts, pp. 199–207 (2005)
Shannon, C.: A mathematical theory of communication. Bell Syst. Techn. J. 27, 379–423/623–656 (1948)
Grünwald, P.: A tutorial introduction to the minimum description length principle (2004). http://arxiv.org/abs/math/0406077
Saers, M., Addanki, K., Wu, D.: Iterative rule segmentation under minimum description length for unsupervised transduction grammar induction. In: Dediu, A.-H., Martín-Vide, C., Mitkov, R., Truthe, B. (eds.) SLSP 2013. LNCS, vol. 7978, pp. 224–235. Springer, Heidelberg (2013)
Zipf, G.K.: The Psychobiology of Language. Houghton-Mifflin, Boston (1935)
Callison-Burch, C., Fordyce, C., Koehn, P., Monz, C., Schroeder, J.: (Meta-) evaluation of machine translation. In: Proceedings of the Workshop on Statistical Machine Translation, pp. 136–158 (2007)
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: A method for automatic evaluation of machine translation. In: Proceedings of the Meeting on Association for Computational Linguistics, Association for Computational Linguistics, pp. 311–318 (2002)
Snover, M., Dorr, B., Schwartz, R., Micciulla, L., Makhoul, J.: A study of translation edit rate with targeted human annotation. In: Proceedings of Association for Machine Translation in the Americas, pp. 223–231 (2006)
Turchi, M., De Bie, T., Cristianini, N.: Learning to translate: a statistical and computational analysis. Technical report, University of Bristol (2009)
Acknowledgments
Work supported by the EU \(7^\mathrm{th}\) Framework Programme (FP7/2007–2013) under the CasMaCat project (grant agreement n\(^{\text{ o }}\) 287576), by Spanish MICINN under grant TIN2012-31723, and by the Generalitat Valenciana under grant ALMPR (Prometeo/2009/014).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
González-Rubio, J., Casacuberta, F. (2015). Improving the Minimum Description Length Inference of Phrase-Based Translation Models. In: Paredes, R., Cardoso, J., Pardo, X. (eds) Pattern Recognition and Image Analysis. IbPRIA 2015. Lecture Notes in Computer Science(), vol 9117. Springer, Cham. https://doi.org/10.1007/978-3-319-19390-8_25
Download citation
DOI: https://doi.org/10.1007/978-3-319-19390-8_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19389-2
Online ISBN: 978-3-319-19390-8
eBook Packages: Computer ScienceComputer Science (R0)