Abstract
Different works on training of log-linear interpolation models for statistical machine translation reported performance improvements by optimizing parameters with respect to translation quality, rather than to likelihood oriented criteria. This work presents an alternative minimum error-rate training procedure based on structural support vector machines (SSVMs) for log-linear interpolation models which is not limited to the model scaling factors and needs only few iterations to converge. Experimental results are reported on the Spanish–English Europarl corpus.
This is a preview of subscription content, log in via an institution to check access.
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
Klakow, D.: Log-linear interpolation of language models. In: 5th International Conference on Spoken Language Processing, Sydney, Australia, pp. 1695–1699 (1998)
Och, F., Ney, H.: Discriminative training and maximum entropy models for statistical machine translation. In: ACL 2002 (2002)
Och, F.J.: Minimum error rate training for statistical machine translation. In: Proc. of the ACL, Sapporo, Japan (2003)
González-Rubio, J., Ortiz-Martinez, D., Casacuberta, F.: Optimization of log-linear machine translation model parameters using svms. In: Proc. of the 8th Int. Workshop on Pattern Recognition in Information Systems (2008)
Joachims, T., Finley, T., Yu, C.N.: Cutting-plane training of structural svms. Machine Learning Journal (to appear)
Duda, R., Hart, P.: Pattern Classification and Scene Analysis (1973)
Vapnik, V.: Statistical Learning Theory (1998)
Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. Journal of Machine Learning Research (2005)
Ortiz-Martínez, D., García-Varea, I., Casacuberta, F.: Thot: a toolkit to train phrase-based statistical translation models. In: 10th MT Summit (2005)
Ortiz-Martínez, D., García-Varea, I., Casacuberta, F.: Phrase-level alignment generation using a smoothed log-linear phrase-based statistical alignment model. In: Proc. of EAMT 2008, Hamburg, Germany (September 2008)
Papineni, K., Kishore, A., Roukos, S., Ward, T., Zhu, W.: Bleu: A method for automatic evaluation of machine translation. Technical Report RC22176, W0109-022 (2001)
Koehn, P.: Europarl: A parallel corpus for statistical machine translation. In: MT Summit (2005)
Koehn, P., Monz, C.: Manual and automatic evaluation of machine translation between european languages. In: Proc. of the NAACL, pp. 102–121 (2006)
Stolcke, A.: Srilm - an extensible language modeling toolkit. In: Proc. of the Int. Conference on Spoken Language Processing, vol. 2, pp. 901–904 (2002)
Koehn, P., Och, F., Marcu, D.: Statistical phrase-based translation. In: Proc. of the NAACL-HLT, vol. 1, 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., Constantine, A., Herbst, E.: Moses: Open source toolkit for statistical machine translation. In: Proc. of the ACL (2007)
Cettolo, M., Federico, M.: Minimum error training of log-linear translation models. In: IWSLT 2004, pp. 103–106 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
González-Rubio, J., Ortiz-Martinez, D., Casacuberta, F. (2009). Minimum Error-Rate Training in Statistical Machine Translation Using Structural SVMs. In: Araujo, H., Mendonça, A.M., Pinho, A.J., Torres, M.I. (eds) Pattern Recognition and Image Analysis. IbPRIA 2009. Lecture Notes in Computer Science, vol 5524. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02172-5_49
Download citation
DOI: https://doi.org/10.1007/978-3-642-02172-5_49
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02171-8
Online ISBN: 978-3-642-02172-5
eBook Packages: Computer ScienceComputer Science (R0)