International Workshop on Spoken Language Translation (IWSLT) 2007

Trento, Italy
October 15-16, 2007

The MIT-LL/AFRL IWSLT-2007 MT System

Wade Shen (1), Brian Delaney (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

The MIT-LL/AFRL MT system implements a standard phrase-based, statistical translation model. It incorporates a number of extensions that improve performance for speechbased translation. During this evaluation our efforts focused on the rapid porting of our SMT system to a new language (Arabic) and novel approaches to translation from speech input. This paper discusses the architecture of the MITLL/ AFRL MT system, improvements over our 2006 system, and experiments we ran during the IWSLT-2007 evaluation. Specifically, we focus on 1) experiments comparing the performance of confusion network decoding and direct lattice decoding techniques for machine translation of speech, 2) the application of lightweight morphology for Arabic MT preprocessing and 3) improved confusion network decoding.

Full Paper     Presentation

Bibliographic reference.  Shen, Wade / Delaney, Brian / Anderson, Tim / Slyh, Ray (2007): "The MIT-LL/AFRL IWSLT-2007 MT system", In IWSLT-2007, 95-102.