BASQUE-SPANISH-ENGLISH MACHINE TRANSLATION USING FINITE-STATE TRANSDUCERS

The goals of this work are, on the one hand to develop a trilingual corpus suitable for example-based text and speech-input machine translation between English, Spanish and Basque; and on the other hand, to compare the same translation method for under two very different pair of languages: Spanish-Basque and Spanish-English. The stochastic nite-state transducers have been trained from raw bilingual examples. As the experimental results show, they seem to be a good choice for both text and speech-input machine translation.