Abstract
The machine translation systems usually build an initial word-to-word alignment, before training the phrase translation pairs. This approach requires a lot of matching between different single words of both considered languages. In this paper, we propose a new approach for phrase-based machine translation which does not require any word alignment. This method is based on inter-lingual triggers retrieved by Multivariate Mutual Information. This algorithm segments sentences into phrases and finds their alignments simultaneously. The main objective of this work is to build directly valid alignments between source and target phrases. The achieved results, in terms of performance are satisfactory and the obtained translation table is smaller than the reference one; this approach could be considered as an alternative to the classical methods.
Index Terms: Statistical Machine Translation, Inter-lingual triggers, Multivariate Mutual Information.
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.
Similar content being viewed by others
References
Abramson, N.: Information theory and coding. McGraw-Hill electronic sciences series. McGraw-Hill (1963)
Hoang, H., Birch, A., Callison-burch, C., Zens, R., Aachen, R., Constantin, A., Federico, M., Bertoldi, N., Dyer, C., Cowan, B., Shen, W., Moran, C., Bojar, O.: Moses: Open source toolkit for statistical machine translation, 177–180 (2007)
Johnson, H., Martin, J., Foster, G., Kuhn, R.: Improving Translation Quality by Discarding Most of the Phrase table. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 967–975 (2007)
Koehn, P., Franz, J.,Marcu, D.: Statistical phrase-based translation. In: Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, NAACL 2003, Edmonton, Canada, vol. 1, pp. 48–54 (2003)
Koehn, P.: Europarl: A Parallel Corpus for Statistical Machine Translation. In: Conference Proceedings: the Tenth Machine Translation Summit, pp. 79–86 (2005)
Lavecchia, C., Smaïli, K., Langlois, D., Haton, J.-P.: Using inter-lingual triggers for machine translation. In: INTERSPEECH, pp. 2829–2832 (2007)
Lavecchia, C., Smaïli, K., Langlois, D., Haton, J.-P.: Using inter-lingual triggers for machine translation. In: INTERSPEECH, pp. 2829–2832 (2007)
Lavecchia, C., Langlois, D., Smaïli, K.: Discovering phrases in machine translation by simulated annealing. In: Interspeech, pp. 2354–2357 (2008)
Nasri, C., Smaïli, K., Latiri, C., Slimani, Y.: A new method for learning Phrase Based Machine Translation with Multivariate Mutual Information. In: NLP-KE 2012, HuangShan, China (2012)
Och, F., Hermann, N.: A Systematic Comparison of Various Statistical Alignment Models. Computational Linguistics 29 (2003)
Quirk, C., Menezes, A.: Do we need phrases? Challenging the conventional wisdom in Statistical Machine Translation. In: HLT-NAACL (2006)
Tillmann, C., Ney, H., Lehrstuhl Fur Informatik Vi: Word Triggers and the EM Algorithm. In: Proceedings of the Workshop Computational Natural Language Learning (CoNLL ), pp. 117–124 (1997)
Venugopal, A., Vogel, S., Waibel, A.: Effective Phrase Translation Extraction from Alignment Models, pp. 319–326. ACL (2003)
Zens, R., Och, F.J., Hermann, N.: Phrase-Based Statistical Machine Translation, pp. 18–32. Springer (2002)
Zens, R., Ney, H.: Improvements in Phrase-Based Statistical Machine Translation. In: The Human Language Technology Conf, HLT-NAACL, pp. 257–264 (2004)
Zhang, Y., Vogel, S., Waibel, A.: Integrated Phrase Segmentation and Alignment Algorithm for Statistical Machine Translation. In: Proceedings of International Conference on Natural Language Processing and Knowledge Engineering (NLP-KE 2003), Beijing, China (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nasri, C., Smaili, K., Latiri, C. (2014). Training Phrase-Based SMT without Explicit Word Alignment. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2014. Lecture Notes in Computer Science, vol 8404. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-54903-8_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-54903-8_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-54902-1
Online ISBN: 978-3-642-54903-8
eBook Packages: Computer ScienceComputer Science (R0)