The MIT-LL/AFRL MT system is a statistical phrase-based translation system that implements many modern SMT training and decoding techniques. Our system was designed with the long term goal of dealing with corrupted ASR input for Speech-to-Speech MT applications. This paper will discuss the architecture of the MIT-LL/AFRL MT system, and experiments with manual and ASR transcription data that were run as part of the IWSLT-2005 Chinese-to-English evaluation campaign.
Cite as: Shen, W., Delaney, B., Anderson, T. (2005) The MIT-LL/AFRL MT system. Proc. International Workshop on Spoken Language Translation (IWSLT 2005), 99-103
@inproceedings{shen05_iwslt, author={Wade Shen and Brian Delaney and Timothy Anderson}, title={{The MIT-LL/AFRL MT system}}, year=2005, booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2005)}, pages={99--103} }