International Workshop on Spoken Language Translation (IWSLT) 2010
This paper describes the MIT-LL/AFRL statistical MT
system and the improvements that were developed during the
IWSLT 2010 evaluation campaign. As part of these efforts,
we experimented with a number of extensions to the standard
phrase-based model that improve performance on the Arabic
and Turkish to English translation tasks. We also participated
in the new French to English BTEC and English to French
We discuss the architecture of the MIT-LL/AFRL MT system, improvements over our 2008 system, and experiments we ran during the IWSLT-2010 evaluation. Specifically, we focus on 1) cross-domain translation using MAP adaptation, 2) Turkish morphological processing and translation, 3) improved Arabic morphology for MT preprocessing, and 4) system combination methods for machine translation.
Bibliographic reference. Shen, Wade / Anderson, Tim / Slyh, Ray / Aminzadeh, A. Ryan (2010): "The MIT-LL/AFRL IWSLT-2010 MT system", In IWSLT-2010, 127-134.