In this paper we propose a phrase-based translation system. In the system, we use phrase translation model instead of word-based model. An improved method of computing phrase translation probability is studied. We translate numeral phrases first by using a standard templates depository. We develop a phrase-based decoder that employs a beam search algorithm. To make the result more reasonable, we apply those words with fertility probability of zero. We improve the previously proposed tracing back algorithm to get the best path. Some experiments concerned are presented.
Cite as: Pang, W., Yang, Z., Chen, Z., Wei, W., Xu, B., Zong, C. (2005) The CASIA phrase-based machine translation system. Proc. International Workshop on Spoken Language Translation (IWSLT 2005), 104-111
@inproceedings{pang05_iwslt,
author={Wei Pang and Zhendong Yang and Zhenbiao Chen and Wei Wei and Bo Xu and Chengqing Zong},
title={{The CASIA phrase-based machine translation system}},
year=2005,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2005)},
pages={104--111}
}