Abstract
New variations on the application of the passive-aggressive algorithm to statistical machine translation are developed and compared to previously existing approaches. In online adaptation, the system needs to adapt to real-world changing scenarios, where training and tuning only take place when the system is set-up for the first time. Post-edit information, as described by a given quality measure, is used as valuable feedback within the passive-aggressive framework, adapting the statistical models on-line. First, by modifying the translation model parameters, and alternatively, by adapting the scaling factors present in state-of-the-art SMT systems. Experimental results show improvements in translation quality by allowing the system to learn on a sentence-by-sentence basis.
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
Barrachina, S., et al.: Statistical approaches to computer-assisted translation. Computational Linguistics 35(1), 3–28 (2009)
Callison-Burch, C., Bannard, C., Schroeder, J.: Improving statistical translation through editing. In: Proc. of 9th EAMT Workshop Broadening Horizons of Machine Translation and its Applications, Malta (April 2004)
Callison-Burch, C., Fordyce, C., Koehn, P., Monz, C., Schroeder, J.: (meta-) evaluation of machine translation. In: Proc. of the Workshop on SMT, pp. 136–158. ACL (June 2007)
Crammer, K., Dekel, O., Keshet, J., Shalev-Shwartz, S., Singer, Y.: Online passive-aggressive algorithms. Journal of Machine Learning Research 7, 551–585 (2006)
Kneser, R., Ney, H.: Improved backing-off for m-gram language modeling. In: IEEE Int. Conf. on Acoustics, Speech and Signal Processing II, pp. 181–184 (May 1995)
Koehn, P.: Europarl: A parallel corpus for statistical machine translation. In: Proc. of the MT Summit X, pp. 79–86 (2005)
Koehn, P., et al.: Moses: Open source toolkit for statistical machine translation. In: Proc. of the ACL Demo and Poster Sessions, Prague, Czech Republic, pp. 177–180 (2007)
Och, F., Ney, H.: Discriminative training and maximum entropy models for statistical machine translation. In: Proc. of the ACL 2002, pp. 295–302 (2002)
Och, F.: Minimum error rate training for statistical machine translation. In: Dignum, F.P.M. (ed.) ACL 2003. LNCS (LNAI), vol. 2922, pp. 160–167. Springer, Heidelberg (2004)
Ortiz-Martínez, D., García-Varea, I., Casacuberta, F.: Online learning for interactive statistical machine translation. In: Proceedings of NAACL HLT, Los Angeles (June 2010)
Papineni, K., Roukos, S., Ward, T.: Maximum likelihood and discriminative training of direct translation models. In: Proc. of ICASSP 1998, pp. 189–192 (1998)
Papineni, K., Roukos, S., Ward, T., Zhu, W.: Bleu: A method for automatic evaluation of machine translation. In: Proc. of ACL 2002, pp. 311–318 (2002)
Reverberi, G., Szedmak, S., Cesa-Bianchi, N., et al.: Deliverable of package 4: Online learning algorithms for computer-assisted translation (2008)
Sanchis-Trilles, G., Casacuberta, F.: Log-linear weight optimisation via bayesian adaptation in statistical machine translation. In: Proc. of COLING 2010, Beijing, China, pp. 1077–1085 (August 2010)
Snover, M., et al.: A study of translation edit rate with targeted human annotation. In: Proc. of AMTA 2006, Cambridge, Massachusetts, USA, pp. 223–231 (August 2006)
Zens, R., Och, F., Ney, H.: Phrase-based statistical machine translation. In: Jarke, M., Koehler, J., Lakemeyer, G. (eds.) KI 2002. LNCS (LNAI), vol. 2479, pp. 18–32. Springer, Heidelberg (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Martínez-Gómez, P., Sanchis-Trilles, G., Casacuberta, F. (2011). Passive-Aggressive for On-Line Learning in Statistical Machine Translation. In: Vitrià, J., Sanches, J.M., Hernández, M. (eds) Pattern Recognition and Image Analysis. IbPRIA 2011. Lecture Notes in Computer Science, vol 6669. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21257-4_30
Download citation
DOI: https://doi.org/10.1007/978-3-642-21257-4_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21256-7
Online ISBN: 978-3-642-21257-4
eBook Packages: Computer ScienceComputer Science (R0)