Hierarchical finite-state models for speech translation using categorization of phrases

Authors:
Raquel Justo;Alicia Pérez;M. Inés Torres;Francisco Casacuberta
Affiliations:
Departament of Electricity of Electronics, University of the Basque Country;Departament of Electricity of Electronics, University of the Basque Country;Departament of Electricity of Electronics, University of the Basque Country;Departament of Information Systems and Computation, Technical University of Valencia
Venue:
CICLing'10 Proceedings of the 11th international conference on Computational Linguistics and Intelligent Text Processing
Year:
2010

Citing 8
Cited 0

A systematic comparison of various statistical alignment models

Computational Linguistics
An efficient method for determining bilingual word classes

EACL '99 Proceedings of the ninth conference on European chapter of the Association for Computational Linguistics
Probabilistic Finite-State Machines-Part II

IEEE Transactions on Pattern Analysis and Machine Intelligence
Machine Translation with Inferred Stochastic Finite-State Transducers

Computational Linguistics
Learning finite-state models for machine translation

Machine Learning
A variable-length category-based n-gram language model

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
Smoothing methods in maximum entropy language modeling

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
(Meta-) evaluation of machine translation

StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation

Quantified Score

Hi-index	0.00

Visualization

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.