The Microsoft Research translation system is a syntactically informed phrasal SMT system that uses a phrase translation model based on dependency treelets and a global reordering model based on the source dependency tree. These models are combined with several other knowledge sources in a log- linear manner. The weights of the individual components in the log-linear model are set by an automatic parameter-tuning method. We give a brief overview of the components of the system and discuss its performance at IWSLT in two tracks: Japanese to English (supplied data and tools), and English to Chinese (supplied data and tools).
Cite as: Menezes, A., Quirk, C. (2005) Microsoft research treelet translation system: IWSLT evaluation. Proc. International Workshop on Spoken Language Translation (IWSLT 2005), 95-98
@inproceedings{menezes05_iwslt, author={Arid Menezes and Chris Quirk}, title={{Microsoft research treelet translation system: IWSLT evaluation}}, year=2005, booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2005)}, pages={95--98} }