International Workshop on Spoken Language Translation (IWSLT) 2009

Tokyo, Japan
December 1-2, 2009

The MIT-LL/AFRL IWSLT-2009 MT System

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

(1) MIT Lincoln Laboratory, Information Systems and Technology Group, Lexington, MA, USA
(2) Air Force Research Laboratory, Human Effectiveness Directorate, Wright-Patterson AFB, OH, USA

This paper describes the MIT-LL/AFRL statistical MT system and the improvements that were developed during the IWSLT 2009 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 discuss the architecture of the MIT-LL/AFRL MT system, improvements over our 2008 system, and experiments we ran during the IWSLT-2009 evaluation. Specifically, we focus on 1) Cross-domain translation using MAP adaptation and unsupervised training, 2) Turkish morphological processing and translation, 3) improved Arabic morphology for MT preprocessing, and 4) system combination methods for machine translation.

Full Paper     Presentation (pdf)

Bibliographic reference.  Shen, Wade / Delaney, Brian / Aminzadeh, A. Ryan / Anderson, Tim / Slyh, Ray (2009): "The MIT-LL/AFRL IWSLT-2009 MT system", In IWSLT-2009, 71-78.