Abstract
In this paper, we explore several methods of improving the estimation of translation model probabilities for phrase-based statistical machine translation given in-domain data sparsity. We introduce a hierarchical variant of maximum a posteriori (MAP) adaptation for domain adaptation with an arbitrary number of out-of-domain models. We note that domain adaptation can have a smoothing effect, and we explore the interaction between smoothing and the incorporation of out-of-domain data. We find that the relative contributions of smoothing and interpolation depend on the datasets used. For both the IWSLT 2011 and WMT 2011 English-French datasets, the MAP adaptation method we present improves on a baseline system by 1.5+ BLEU points.
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
Gauvain, J.L., Lee, C.H.: Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Transactions on Speech and Audio Processing 2, 291–298 (1994)
Federico, M.: Bayesian estimation methods for n-gram language model adaptation. In: Proceedings of International Conference on Spoken Language Processing, pp. 240–243 (1996)
Bacchiani, M., Riley, M., Roark, B., Sproat, R.: Map adaptation of stochastic grammars. Computer Speech & Language 20, 41–68 (2006)
Shen, W., Delaney, B., Aminzadeh, A.R., Anderson, T., Slyh, R.: The MIT-LL/AFRL IWSLT-2009 System. In: Proc. of the International Workshop on Spoken Language Translation, Tokyo, Japan, pp. 71–78 (2009)
Foster, G., Kuhn, R., Johnson, J.H.: Phrasetable smoothing for statistical machine translation. In: Conference on Empirical Methods in Natural Language Processing, Sydney, Australia (2006)
Foster, G., Goutte, C., Kuhn, R.: Discriminative instance weighting for domain adaptation in statistical machine translation. In: Proceedings of the 2010 EMNLP, Cambridge, MA, pp. 451–459 (2010)
Foster, G., Kuhn, R.: Mixture-model adaptation for SMT. In: ACL Workshop on Statistical Machine Translation, Prague, Czech Republic (2007)
Bisazza, A., Ruiz, N., Federico, M.: Fill-up versus interpolation methods for phrase-based smt adaptation. In: International Workshop on Spoken Language Translation (2011)
Kneser, R., Ney, H.: Improved backing-off for m-gram language modeling. In: International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1995, vol. 1, pp. 181–184 (1995)
Chen, S.F., Goodman, J.: An empirical study of smoothing techniques for language modeling. Computer Speech and Language 13, 359–393 (1999)
Chen, B., Kuhn, R., Foster, G., Johnson, H.: Unpacking and transforming feature functions: New ways to smooth phrase tables. In: Proceedings of MT Summit XIII, Xiamen, China (2011)
Campbell, W., Campbell, J., Gleason, T., Reynolds, D., Shen, W.: Speaker verification using support vector machines and high-level features. IEEE Transactions on Audio, Speech, and Language Processing 15, 2085–2094 (2007)
Callison-Burch, C., Koehn, P., Monz, C., Zaidan, O.: Findings of the 2011 workshop on statistical machine translation. In: Proceedings of the 6th Workshop on Statistical Machine Translation, Edinburgh, Scotland, pp. 22–64 (2011)
Federico, M., Bentivogli, L., Michael Paul, S.S.:: Overview of the iwslt 2011 evaluation campaign. In: Proceedings of the International Workshop on Spoken Language Translation, San Francisco, CA (2011)
Shen, W., Anderson, T., Slyh, R., Aminzadeh, A.: The MIT-LL/AFRL IWSLT 2010 MT system. In: Proc. of the International Workshop on Spoken Language Translation, Paris, France (2010)
Hsu, B.J., Glass, J.: Iterative language model estimation: Efficient data structure and algorithms. In: Proc. Interspeech (2008)
Brown, P.F., Della Pietra, S.A., Della Pietra, V.J., Mercer, R.L.: The Mathematics of Statistical Machine Translation: Parameter Estimation. Computational Linguistics 19, 263–311 (1993)
Chen, B., Cattoni, R., Bertoldi, N., Cettolo, M., Federico, M.: The ITC-irst SMT System for IWSLT-2005. In: Proceedings of the IWSLT 2005 (2005)
Och, F.J.: Minimum Error Rate Training in Statistical Machine Translation. In: Proceedings of ACL (2003)
Koehn, P., Hoang, H., Birch, A., Burch, C.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 ACL, ACL 2007, Stroudsburg, PA, USA, pp. 177–180 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Aminzadeh, A.R., Drexler, J., Anderson, T., Shen, W. (2012). Improved Phrase Translation Modeling Using MAP Adaptation. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds) Text, Speech and Dialogue. TSD 2012. Lecture Notes in Computer Science(), vol 7499. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32790-2_48
Download citation
DOI: https://doi.org/10.1007/978-3-642-32790-2_48
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32789-6
Online ISBN: 978-3-642-32790-2
eBook Packages: Computer ScienceComputer Science (R0)