The NUS Statistical Machine Translation System for IWSLT 2009
Preslav Nakov, Chang Liu, Wei Lu, Hwee Tou Ng · 2009
We describe the system developed by the team of the National University of Singapore for the Chinese-English BTEC task of the IWSLT 2009 evaluation campaign. We adopted a state-of-the-art phrase-based statistical machine translation approach and focused on experiments with dif-ferent Chinese word segmentation standards. In our official submission, we trained a separate system for each segmenter and we combined the outputs in a subsequent re-ranking step. Given the small size of the training data, we further re-trained the system on the development data after tuning. The evalua-tion results show that both strategies yield sizeable and con-sistent improvements in translation quality. 1.