We describe the machine translation system of the University of Amsterdam, that was used to decode the Chinese-to-English test sets of the DIALOG task. It consists of typical phrase-based translation, SRILM 5-gram language, lexicalized and distance-based distortion and word penalty models which are manipulated according to a model adaption technique, based on the identification of subdomains of the provided data sets.
Cite as: Martzoukos, S., Monz, C. (2010) The uva system description for IWSLT 2010. Proc. International Workshop on Spoken Language Translation (IWSLT 2010), 205-208
@inproceedings{martzoukos10_iwslt,
author={Spyros Martzoukos and Christof Monz},
title={{The uva system description for IWSLT 2010}},
year=2010,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2010)},
pages={205--208}
}