International Workshop on Spoken Language Translation (IWSLT) 2004 Keihanna Science City, Kyoto, Japan September 30-October 1, 2004

The ISI/USC MT System

Ignacio Thayer, Emil Ettelaie, Kevin Knight, Daniel Marcu, Dragos Stefan Munteanu, Franz Joseph Och, Quamrul Tipu

USC Information Sciences Institute, Marina del Rey, CA. USA

The ISI/USC machine translation system is a statistical system based on a phrase translation model that is trained on bilingual parallel data. This translation model is combined with several other knowledge sources in a log-linear manner. The weights of the individual components in the log-linear model are set by an automatic parameter-tuning method. The system described here has been developed for translating news text, and is a simplified version of the one we participated with in the NIST 2004 MT evaluation. We give a brief overview of the components of the system and discuss its performance at IWSLT.

Full Paper    Presentation

Bibliographic reference.  Thayer, Ignacio / Ettelaie, Emil / Knight, Kevin / Marcu, Daniel / Munteanu, Dragos Stefan / Och, Franz Joseph / Tipu, Quamrul (2004): "The ISI/USC MT system", In IWSLT-2004, 59-60.