Abstract
In terms of translation quality, hierarchical phrase-based translation model (Hiero) has shown state-of-the-art performance in various translation tasks. However, the slow decoding speed of Hiero prevents it from effective deployment in online scenarios.
In this paper, we propose beam-width adaptation strategies to speed up Hiero decoding. We learn maximum entropy models to evaluate the quality of each span and then predict the optimal beam-width for it. The empirical studies on Chinese-to-English translation tasks show that, even in comparison with a competitive baseline which employs well designed cube pruning, our approaches still double the decoding speed without compromising translation quality. The approaches have already been applied to an online commercial translation system.
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
Chiang, D.: A hierarchical phrase-based model for statistical machine translation. In: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, pp. 263–270. Association for Computational Linguistics (2005)
Koehn, P., Och, F.J., Marcu, D.: Statistical phrase-based translation. In: Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, vol. 1, pp. 48–54. Association for Computational Linguistics (2003)
Chiang, D.: Hierarchical phrase-based translation. Computational Linguistics 33, 201–228 (2007)
Hopkins, M., Langmead, G.: Cube pruning as heuristic search. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, vol. 1, pp. 62–71. Association for Computational Linguistics (2009)
Gesmundo, A., Henderson, J.: Faster cube pruning. In: IWSLT 2010: Proceedings of the 7th International Workshop on Spoken Language Translation (2010)
Roark, B., Hollingshead, K.: Linear complexity context-free parsing pipelines via chart constraints. In: Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp. 647–655. Association for Computational Linguistics (2009)
Bodenstab, N., Dunlop, A., Hall, K., Roark, B.: Beam-width prediction for efficient context-free parsing. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, Portland, Oregon. Association for Computational Linguistics (2011)
Roark, B., Hollingshead, K.: Classifying chart cells for quadratic complexity context-free inference. In: Proceedings of the 22nd International Conference on Computational Linguistics, vol. 1, pp. 745–751. Association for Computational Linguistics (2008)
Xiong, D., Zhang, M., Li, H.: Learning translation boundaries for phrase-based decoding. In: Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp. 136–144. Association for Computational Linguistics (2010)
Zaidan, O.F.: Z-mert: A fully configurable open source tool for minimum error rate training of machine translation systems. The Prague Bulletin of Mathematical Linguistics 91, 79–88 (2009)
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
Su, F., Chen, G., Xiao, X., Su, K. (2014). Beam-Width Adaptation for Hierarchical Phrase-Based Translation. 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_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-54903-8_19
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)