Skip to main content

Word Translation Disambiguation Using Multinomial Classifiers

  • Conference paper
Pattern Recognition and Image Analysis (IbPRIA 2005)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 3523))

Included in the following conference series:

  • 1656 Accesses

Abstract

This work focuses on a hybrid machine translation system from Spanish into Catalan called SisHiTra. In particular, we focus on its word translation disambiguation module, which has to decide on the correct translation of each ambiguous input word in accordance with its context. We propose the use of statistical pattern recognition techniques for this task and, in particular, multinomial Naive Bayes text classifiers. Extensive empirical results on the use of these classifiers are presented, in which the influence of the window (context) size and parameter smoothing are carefully studied.

Work supported by the “Agència Valenciana de Ciència i Tecnologia” under grant GRUPOS03/031 and the Spanish project ITEFTE (TIC2003-08681-C02-02).

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Juan, A., Ney, H.: Reversing and Smoothing the Multinomial Naive Bayes Text Classifier. In: Proc. of the 2nd Int. Workshop on Pattern Recognition in Information Systems (PRIS 2002), Alicante (Spain), April 2002, pp. 200–212 (2002)

    Google Scholar 

  2. Navarro, J.R., et al.: SisHiTra: A Hybrid Machine Translation System from Spanish to Catalan. In: Vicedo, J.L., Martínez-Barco, P., Muńoz, R., Saiz Noeda, M. (eds.) EsTAL 2004. LNCS (LNAI), vol. 3230, pp. 349–359. Springer, Heidelberg (2004)

    Chapter  Google Scholar 

  3. Och, F.J., Ney, H.: Improved Statistical Alignment Models. In: ACL 2000, Hongkong, China, October 2000, pp. 440–447 (2000)

    Google Scholar 

  4. Roche, E., Schabes, Y.: Deterministic Part-Of-Speech Tagging with Finite-State Transducers. Computational Linguistics 21(2), 227–253 (1995)

    Google Scholar 

  5. Tomás, J., Casacuberta, F.: Binary deature classification for word disambiguation in statistical machine translation. In: Proceedings of the 2nd International Workshop on Pattern Recognition in Information Systems, Spain, pp. 213–224 (2002)

    Google Scholar 

  6. Vilar, D., Ney, H., Juan, A., Vidal, E.: Effect of Fature Smoothing Methods in Text Classification Tasks. In: Proc. of the 2nd Int. Workshop on Pattern Recognition in Information Systems, PRIS 2004 (2004)

    Google Scholar 

  7. El Periódico, website: www.elperiodico.com , Ediciones Primera Plana S.A., Consell de Cent, 425-427. 08009 Barcelona (Spain)

  8. http://www.cult.gva.es/salt/salt_programes_salt2.htm

  9. http://www.internostrum.com/

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Andrés, J., Navarro, J.R., Juan, A., Casacuberta, F. (2005). Word Translation Disambiguation Using Multinomial Classifiers. In: Marques, J.S., Pérez de la Blanca, N., Pina, P. (eds) Pattern Recognition and Image Analysis. IbPRIA 2005. Lecture Notes in Computer Science, vol 3523. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11492542_76

Download citation

  • DOI: https://doi.org/10.1007/11492542_76

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-26154-4

  • Online ISBN: 978-3-540-32238-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics