International Workshop on Spoken Language Translation (IWSLT) 2006
Keihanna Science City, Kyoto, Japan
The MIT-LL/AFRL MT system is a statistical phrasebased 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 and limited amounts of training data for speech-to-speech MT applications. This paper will discuss the architecture of the MIT-LL/AFRL MT system, improvements over our 2005 system, and experiments with manual and ASR transcription data that were run as part of the IWSLT-2006 evaluation campaign.
Full Paper Presentation
Bibliographic reference. Shen, Wade / Delaney, Brian / Anderson, Timothy (2006): "The MIT-LL/AFRL IWSLT-2006 MT system", In IWSLT-2006, 71-76.