Inference of Stochastic Finite-State Transducers Using N-Gram Mixtures

Authors:
Vicente Alabau;Francisco Casacuberta;Enrique Vidal;Alfons Juan
Affiliations:
Departament de Sistemes Informàtics i Computació, Universitat Politècnica de València,;Departament de Sistemes Informàtics i Computació, Universitat Politècnica de València,;Departament de Sistemes Informàtics i Computació, Universitat Politècnica de València,;Departament de Sistemes Informàtics i Computació, Universitat Politècnica de València,
Venue:
IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part II
Year:
2007

Citing 7
Cited 0

A statistical approach to machine translation

Computational Linguistics
A systematic comparison of various statistical alignment models

Computational Linguistics
Probabilistic Finite-State Machines-Part II

IEEE Transactions on Pattern Analysis and Machine Intelligence
Probabilistic Finite-State Machines-Part I

IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistical phrase-based translation

NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Machine Translation with Inferred Stochastic Finite-State Transducers

Computational Linguistics
A weighted finite state transducer translation template model for statistical machine translation

Natural Language Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.