International Workshop on Spoken Language Translation (IWSLT) 2010

Paris, France
December 2-3, 2010

The MIT-LL/AFRL IWSLT-2010 MT System

Wade Shen (1), Tim Anderson (2), Ray Slyh (2), A. Ryan Aminzadeh (3)

(1) MIT/Lincoln Laboratory, Human Language Technology Group, Lexington, MA, USA
(2) Air Force Research Laboratory, Wright-Patterson AFB, OH, USA
(3) Department of Defense, Washington, DC, USA

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 TALK tasks.
   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.

Full Paper

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.