Abstract
We apply several word reordering techniques to a Bangla-English Statistical Machine Translation (SMT) system. We evaluate the approaches through their impact on the BLEU score for the phrase-based Bangla-English SMT system. According to the experimental results, automatic reordering rules have the most significant impact on the BLEU score. We also provide a new test set with multiple references between Bangla and English for SMT evaluation purposes and evaluate the reordering approaches on the extended test set.
This research was partially supported by a discovery grant from NSERC, Canada.
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
Crego, J.M., Marino, J.B.: Syntax-enhanced ngram- based smt. In: Proceedings of the 11th MT Summit (2007)
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 Annual Meeting of the Association for Computational Linguistics (2007)
Och, F.J.: Minimum Error Rate Training in Statistical Machine Translation. In: ACL 2003, pp. 160–167 (2003)
Papineni, K., Roukos, S., Ward, T., Zhu, W.: BLEU: A method for Automatic Evaluation of Machine Translation. In: Proceedings of the 20th Annual Meeting of the Association for Computational Linguistics (2002)
Rottmann, K., Vogel, S.: Word Reordering in Statistical Machine Translation with a POS-based Distortion Model. In: TMI 2007: 11th International Conference on Theoretical and Methodological Issues in MT, Skvde, Sweden (2007)
Stolcke, A.: SRILMan extensible language modeling toolkit. In: Hansen, J.H.L., Pellom, B. (eds.) Proc. ICSLP, September 2002, vol. 2, pp. 901–904 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Roy, M., Popowich, F. (2010). Word Reordering Approaches for Bangla-English Statistical Machine Translation. In: Farzindar, A., Kešelj, V. (eds) Advances in Artificial Intelligence. Canadian AI 2010. Lecture Notes in Computer Science(), vol 6085. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13059-5_29
Download citation
DOI: https://doi.org/10.1007/978-3-642-13059-5_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-13058-8
Online ISBN: 978-3-642-13059-5
eBook Packages: Computer ScienceComputer Science (R0)