In this paper, we give a description of the DCU machine translation systems submitted to the evaluation campaign of The International Workshop on Spoken Language Translation (IWSLT) 2010. We participated in the BTEC Arabic-to-English task in addition to the DIALOG task for translation between English and Chinese in both directions. We explore different extensions to Phrase-Based and Hierarchical Phrase-Based Machine Translation Systems. We deploy a paraphrase system as an extension to our English-to- Chinese Phrase-Based translation system. For the Hierarchical Phrase-Based system, two different syntactic augmentation methods are investigated: the first is Syntax Augmented Machine Translation ,which is based on constituent grammar, while the other one is based on Combinatory Categorial Grammar. In addition, we combine the output of our hierarchical systems using a system combination method based on confusion networks.
Cite as: Almaghout, H., Jiang, J., Way, A. (2010) The DCU machine translation systems for IWSLT 2010. Proc. International Workshop on Spoken Language Translation (IWSLT 2010), 37-44
@inproceedings{almaghout10_iwslt,
author={Hala Almaghout and Jie Jiang and Andy Way},
title={{The DCU machine translation systems for IWSLT 2010}},
year=2010,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2010)},
pages={37--44}
}