International Workshop on Spoken Language Translation (IWSLT) 2007

Trento, Italy
October 15-16, 2007

A Comparison of Linguistically and Statistically Enhanced Models for Speech-to-Speech Machine Translation

Alicia Pérez (1), Víctor Guijarrubia (1), Raquel Justo (1), M. Inés Torres (1), Francisco Casacuberta (2)

(1)Dep. Electricity and Electronics. University of the Basque Country, Spain
(2)Dep. of Information Systems and Computation. Technical University of Valencia, Spain

The goal of this work is to improve current translation models by taking into account additional knowledge sources such as semantically motivated segmentation or statistical categorization. Specifically, two different approaches are discussed. On the one hand, phrase-based approach, and on the other hand, categorization. For both approaches, both statistical and linguistic alternatives are explored. As for translation framework, finite-state transducers are considered. These are versatile models that can be easily integrated on-the-fly with acoustic models for speech translation purposes. In what the experimental framework concerns, all the models presented were evaluated and compared taking confidence intervals into account.

Full Paper     Presentation

Bibliographic reference.  Pérez, Alicia / Guijarrubia, Víctor / Justo, Raquel / Torres, M. Inés / Casacuberta, Francisco (2007): "A comparison of linguistically and statistically enhanced models for speech-to-speech machine translation", In IWSLT-2007, 13-20.