The QMUL submission to IWSLT 2010 is a phrase-based statistical MT system. A multi-stack, multi-beam decoder with several features, with weights tuned on the provided development data through Minimum Error Rate Training (MERT) algorithm. This year QMUL participated in Arabic- English, French-English and Turkish-English language pairs of the BTEC task. A discriminative reordering model is added as a feature to improve the reordering capabilities of the decoder. In addition, an algorithm is devised to determine the best distortion limit for each hypothesis expansion. Improvements in quality were also gained by different means in different stages of the training and decoding.
Cite as: Yahyaei, S., Monz, C. (2010) The QMUL system description for IWSLT 2010. Proc. International Workshop on Spoken Language Translation (IWSLT 2010), 157-162
@inproceedings{yahyaei10_iwslt,
author={Sirvan Yahyaei and Christof Monz},
title={{The QMUL system description for IWSLT 2010}},
year=2010,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2010)},
pages={157--162}
}