Publications

Advanced search

Abstract

Vicent Alabau, Francisco Casacuberta, Enrique Vidal, Alfons Juan. Inference of Stochastic Finite-State Transducers Using N-gram Mixtures. Proceedings of the 3rd Iberian Conference on Pattern Recognition and Image Analysis, Volume 4477 of LNCS, 2007. pp. 282-289. Springer-Verlag.

Statistical pattern recognition has proved to be an interesting framework for machine translation, and stochastic finite-state transducers are adequate models in many language processing areas such as speech translation, computer-assisted translations, etc. The well-known n-gram language models are widely used in this framework for machine translation. One of the application of these n-gram models is to infer stochastic finite-state transducers. However, only simple dependencies can be modelled, but many translations require to take into account strong context and style dependencies. Mixtures of parametric models allow to increase the description power of the statistical models by modelling subclasses of objects. In this work, we propose the use of n-gram mixtures in GIATI, a procedure to infer stochastic finite-state transducers. N-gram mixtures are expected to model topics or writing styles. We present experimental results showing that translation performance can be improved if enough training data is available.