Abstract
Reordering models in statistical machine translation are crucial for many language pairs. Specifically those with very different sentence structure like Persian and English. In this paper, we enhance the well-known lexical model by taking into account the position of the phrase in the target language. We observe over 1.7 percent relative improvement in BLEU score when comparing the baseline lexical reordering model with the proposed model in an English-Persian task.
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
Notes
- 1.
The smoothing method is a geometrically decreasing distribution.
- 2.
For the experiments reported in this paper, we use α = 0.1, which is set empirically.
References
Al-Onaizan, Y., Papineni, K.: Distortion models for statistical machine translation. In: Proceedings of ACL, pp. 529−536 (2006)
Galley, M., Manning, C.D.: A simple and effective hierarchical phrase reordering model. In: Proceedings of EMNLP 2008, pp. 848-856 (2008)
Koehn, P., Och, F.J., Marcu, D.: Statistical phrase-based translation. In: Proceedings of HLT-NAACL 2003, pp. 127−133 (2003)
Koehn, P., Axelrod, A., Mayne, A.B., Callison-Burch, C., Osborne, M., Talbot, D.: Edinburgh system description for the 2005 IWSLT speech translation evaluation. In: Proceedings of IWSLT (2005)
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 ACL 2007, Demonstration Session, pp. 177−180 (2007)
Matusov, E., Kopru, S.: Improving reordering in statistical machine translation from farsi. In: AMTA the Ninth Conference of the Association for Machine Translation (2010)
Knight, K.: Squibs and discussions: de-coding complexity in word-replacement translation models. Comput. Linguist. 25(4), 607–616 (1999)
Och, F.J., Ney, H.: Giza ++: Training of statistical translation models (2000)
Och, F.J.: Minimum error rate training in statistical machine translation. In: Proceedings of ACL 2003, pp. 160−167 (2003)
Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of ACL, pp. 311−318 (2002)
Stolcke, A.: SRILM - An extensible language modeling toolkit. In: Proceedinge of ICSLP, vol. 2, pp. 901−904 (2002)
Su, J., Liu, Y., Lü, Y., Mi, H., Liu, Q.: Learning lexicalized reordering models from reordering graphs. In: Proceedings of ACL 2010, Short Papers, pp. 12−16 (2010)
Tillmann, C.: A unigram orientation model for statistical machine translation. In: Proceedings of HLT-NAACL 2004, Short Papers, pp. 101−104 (2004)
Zens, R., Ney, H.: Discriminative reordering models for statistical machine translation. In: Proceedings of Workshop on Statistical Machine Translation 2006, pp. 521−528 (2006)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Noormohammadi, N., Rahimi, Z., Khadivi, S. (2014). Improving Reordering Models with Phrase Number Feature for Statistical Machine Translation. In: Movaghar, A., Jamzad, M., Asadi, H. (eds) Artificial Intelligence and Signal Processing. AISP 2013. Communications in Computer and Information Science, vol 427. Springer, Cham. https://doi.org/10.1007/978-3-319-10849-0_23
Download citation
DOI: https://doi.org/10.1007/978-3-319-10849-0_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10848-3
Online ISBN: 978-3-319-10849-0
eBook Packages: Computer ScienceComputer Science (R0)