International Workshop on Spoken Language Translation (IWSLT) 2010

Paris, France
December 2-3, 2010

The GREYC/LLACAN Machine Translation Systems for the IWSLT 2010 Campaign

Julien Gosme (1), Wigdan Mekki (1), Fathi Debili (2), Yves Lepage (1), Nadine Lucas (1)

(1) GREYC, Université de Caen Basse-Normandie, Caen, France
(2) LLACAN, UMR 8135, CNRS, Villejuif, France

In this paper we explore the contribution of the use of two Arabic morphological analyzers as preprocessing tools for statistical machine translation. Similar investigations have already been reported for morphologically rich languages like German, Turkish and Arabic. Here, we focus on the case of the Arabic language and mainly discuss the use of the G-LexAr analyzer. A preliminary experiment has been designed to choose the most promising translation system among the 3 G-LexAr-based systems, we concluded that the systems are equivalent. Nevertheless, we decided to use the lemmatized output of G-LexAr and use its translations as primary run for the BTEC AE track. The results showed that G-LexAr outputs degrades translation compared to the basic SMT system trained on the un-analyzed corpus.

Full Paper

Bibliographic reference.  Gosme, Julien / Mekki, Wigdan / Debili, Fathi / Lepage, Yves / Lucas, Nadine (2010): "The GREYC/LLACAN machine translation systems for the IWSLT 2010 campaign", In IWSLT-2010, 59-65.