This paper presents the submissions of the PRHLT group for the evaluation campaign of the International Workshop on Spoken Language Translation. We focus on the development of reliable translation systems between syntactically different languages (DIALOG task) and on the efficient training of SMT models in resource-rich scenarios (TALK task).

In this paper, we describe the machine translation system developed at the Polytechnic University of Valencia, which was used in our participation in the International Workshop on Spoken Language Translation (IWSLT) 2009. We have taken part only in the Chinese-English BTEC Task. In the evaluation campaign, we focused on the use of our hybrid translation system over the provided corpus and less effort was devoted to the use of preand post-processing techniques that could have improved the results. Our decoder is a hybrid machine translation system that combines phrase-based models together with syntax-based translation models. The syntactic formalism that underlies the whole decoding process is a Chomsky Normal Form Stochastic Inversion Transduction Grammar (SITG) with phrasal productions and a log-linear combination of probability models. The decoding algorithm is a CYK-like algorithm that combines the translated phrases inversely or directly in order to get a complete translation of the input sentence.