Advertisement

Hierarchical Finite-State Models for Speech Translation Using Categorization of Phrases

  • Raquel Justo
  • Alicia Pérez
  • M. Inés Torres
  • Francisco Casacuberta
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6008)

Abstract

In this work a hierarchical translation model is formally defined and integrated in a speech translation system. As it is well known, the relations between two languages are better arranged in terms of phrases than in terms of running words. Nevertheless phrase-based models may suffer from data sparsity at training time. The aim of this work is to improve current speech translation systems by integrating categorization within the translation model. The categories are sets of phrases either linguistically or statistically motivated. Both category and translation and acoustic models are within the framework of finite-state models. In what temporal cost is concerned, finite-state models count on efficient decoding algorithms. Regarding the spatial cost, all the models where integrated on-the-fly at decoding time, allowing an efficient use of memory.

Keywords

Machine Translation Target Language Acoustic Model Source Language Translation Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Callison-Burch, C., Fordyce, C., Koehn, P., Monz, C., Schroeder, J.: (meta-) evaluation of machine translation. In: Proceedings of the Second Workshop on Statistical Machine Translation, Prague, Czech Republic, pp. 136–158. Association for Computational Linguistics (2007)Google Scholar
  2. 2.
    Zhou, B., Chen, S., Gao, Y.: Constrained Phrase-based Translation Using Weighted Finite State Transducer. In: Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. 1017–1020 (2005)Google Scholar
  3. 3.
    Pérez, A., Torres, M.I., Casacuberta, F.: Speech translation with phrase based stochastic finite-state transducers. In: Proceedings of the IEEE 32nd International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2007), Honolulu, Hawaii, USA, vol. IV, pp. 113–116. IEEE, Los Alamitos (2007)Google Scholar
  4. 4.
    Casacuberta, F., Vidal, E.: Machine translation with inferred stochastic finite-state transducers. Computational Linguistics 30, 205–225 (2004)CrossRefMathSciNetGoogle Scholar
  5. 5.
    Vidal, E., Thollard, F.C., de la Higuera, F.C., Carrasco, R.: Probabilistic finite-state machines - part II. IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMI) 27, 1025–1039 (2005)Google Scholar
  6. 6.
    Casacuberta, F., Vidal, E.: Learning finite-state models for machine translation. Machine Learning 66, 69–91 (2007)CrossRefGoogle Scholar
  7. 7.
    Mehryar Mohri, F.C.N.P., Riley, M.D.: AT&T FSM LibraryTM Finite-State Machine Library (2003), http://www.research.att.com/sw/tools/fsm
  8. 8.
    Martin, S., Ney, H., Zaplo, J.: Smoothing methods in maximum entropy language modeling. In: Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing, Phoenix, AR, pp. 545–548 (1999)Google Scholar
  9. 9.
    Niesler, T.R., Woodland, P.C.: A variable-length category-based n-gram language model. In: IEEE ICASSP 1996, Atlanta, GA, vol. I, pp. 164–167. IEEE, Los Alamitos (1996)Google Scholar
  10. 10.
    Och, F.J., Ney, H.: A systematic comparison of various statistical alignment models. Computational Linguistics 29, 19–51 (2003)CrossRefGoogle Scholar
  11. 11.
    Justo, R., Torres, M.I.: Phrases in category-based language models for Spanish and Basque ASR. In: Proceedings of the Interspeech 2007, Antwerp, Belgium, pp. 2377–2380 (2007)Google Scholar
  12. 12.
    Och, F.J.: An efficient method for determining bilingual word classes. In: Proceedings of EACL 1999, Bergen, Norway, ACL, pp. 71–76 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Raquel Justo
    • 1
  • Alicia Pérez
    • 1
  • M. Inés Torres
    • 1
  • Francisco Casacuberta
    • 2
  1. 1.Departament of Electricity of ElectronicsUniversity of the Basque Country 
  2. 2.Departament of Information Systems and ComputationTechnical University of Valencia 

Personalised recommendations