Abstract
In this paper we will present a maximum entropy filter for the translation rules of a statistical machine translation system based on tree transducers. This filter can be successfully used to reduce the number of translation rules by more than 70% without negatively affecting translation quality as measured by BLEU. For some filter configurations, translation quality is even improved.
Our investigations include a discussion of the relationship of Alignment Error Rate and Consistent Translation Rule Score with translation quality in the context of Syntactic Statistical Machine Translation.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
DeNero, J., Klein, D.: Tailoring word alignments to syntactic machine translation. In: Proceedings of ACL, pp. 17–24 (2007)
Fossum, V., Knight, K., Abney, S.: Using syntax to improve word alignment precision for syntax-based machine translation. In: Proceedings of ACL Workshop on Statistical Machine Translation, pp. 44–52 (2008)
Zollmann, A., Venugopal, A., Och, F., Ponte, J.: A systematic comparison of phrase-based, hierarchical and syntax-augmented statistical MT. In: Proceedings of ACL-COLING, pp. 1145–1152 (2008)
Ayan, N.F., Dorr, B.J.: Going beyond AER: an extensive analysis of word alignments and their impact on MT. In: Proceedings of ACL-COLING, pp. 9–16 (2006)
Junczys-Dowmunt, M.: It’s all about the trees — towards a hybrid syntax-based MT system. In: Proceedings of IMCSIT, pp. 219–226 (2009)
Huang, L.: Statistical syntax-directed translation with extended domain of locality. In: Proceedings of AMTA, pp. 66–73 (2006)
Liu, Y., Liu, Q., Lin, S.: Tree-to-string alignment template for statistical machine translation. In: Proceedings of ACL, pp. 609–616 (2006)
Aho, A.V., Ullman, J.D.: Translations on a context-free grammar. Information and Control 19, 439–475 (1971)
Graehl, J., Knight, K.: Training tree transducers. In: Proceedings of HLT-NAACL, pp. 105–112 (2004)
Galley, M., Hopkins, M., Knight, K., Marcu, D.: What’s in a translation rule. In: Proceedings of HLT-NAACL, pp. 273–280 (2004)
Germann, U.: Aligned hansards of the 36th parliament of Canada (2001)
Och, F.J., Ney, H.: A systematic comparison of various statistical alignment models. Computational Linguistics 29, 19–51 (2003)
Berger, A.L., Della Pietra, V.J., Della Pietra, S.A.: A maximum entropy approach to natural language processing. Computational Linguistics 22, 39–71 (1996)
Darroch, J., Ratcliff, D.: Generalized iterative scaling for log-linear models. The Annals of Mathematical Statistics 43, 1470–1480 (1972)
Johnson, H., Martin, J., Foster, G., Kuhn, R.: Improving translation quality by discarding most of the phrasetable. In: Proceedings of EMNLP-CoNLL, pp. 967–975 (2007)
Mihalcea, R., Pedersen, T.: An evaluation exercise for word alignment. In: Proceedings of HLT-NAACL, pp. 1–10 (2003)
Koehn, P., Och, F., Marcu, D.: Statistical phrase-based translation. In: Proceedings of HLT-NAACL, pp. 48–54 (2003)
Ayan, N.F., Dorr, B.J.: A maximum entropy approach to combining word alignments. In: Proceedings of HLT-NAACL, pp. 96–103 (2006)
Klein, D., Manning, C.D.: Accurate unlexicalized parsing. In: Proceedings of ACL, pp. 423–430 (2003)
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
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Junczys-Dowmunt, M. (2010). A Maximum Entropy Approach to Syntactic Translation Rule Filtering. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2010. Lecture Notes in Computer Science, vol 6008. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12116-6_38
Download citation
DOI: https://doi.org/10.1007/978-3-642-12116-6_38
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12115-9
Online ISBN: 978-3-642-12116-6
eBook Packages: Computer ScienceComputer Science (R0)