ISCA Archive IWSLT 2008
ISCA Archive IWSLT 2008

The LIUM Arabic/English statistical machine translation system for IWSLT 2008

Holger Schwenk, Yannick Estève, Sadaf Abdul Rauf

This paper describes the system developed by the LIUM laboratory for the 2008 IWSLT evaluation. We only participated in the Arabic/English BTEC task. We developed a statistical phrase-based system using the Moses toolkit and SYSTRAN's rule-based translation system to performa morphological decomposition of the Arabic words. A continuous space languagemodelwas deployed to improve themodeling of the target language. Both approaches achieved significant improvements in the BLEU score. The system achieves a score of 49.4 on the test set of the 2008 IWSLT evaluation.