This paper describes LIMSI's Statistical Machine Translation systems (SMT) for the IWSLT evaluation, where we participated in two tasks (Talk for English to French and BTEC for Turkish to English). For the Talk task, we studied an extension of our in-house n-code SMT system (the integration of a bilingual reordering model over generalized translation units), as well as the use of training data extracted fromWikipedia in order to adapt the target language model. For the BTEC task, we concentrated on pre-processing schemes on the Turkish side in order to reduce the morphological discrepancies with the English side. We also evaluated the use of two different continuous space language models for such a small size of training data.
Cite as: Allauzen, A., Crego, J.M., El-Kahlout, I.D., Hai-Son, L., Wisniewski, G., Yvon, F. (2010) LIMSI @ IWSLT 2010. Proc. International Workshop on Spoken Language Translation (IWSLT 2010), 105-112
@inproceedings{allauzen10_iwslt,
author={Alexandre Allauzen and Josep Maria Crego and Ilknur Durgar El-Kahlout and Le Hai-Son and Guillaume Wisniewski and François Yvon},
title={{LIMSI @ IWSLT 2010}},
year=2010,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2010)},
pages={105--112}
}