International Workshop on Spoken Language Translation (IWSLT) 2009

Tokyo, Japan
December 1-2, 2009

AppTek Turkish-English Machine Translation System Description for IWSLT 2009

Selçuk Köprü

AppTek, Inc., METU, Ankara, Turkey

In this paper, we describe the techniques that are explored in the AppTek system to enhance the translations in the Turkish to English track of IWSLT09. The submission was generated using a phrase-based statistical machine translation system. We also researched the usage of morpho-syntactic information and the application of word reordering in order to improve the translation results. The results are evaluated based on BLEU and METEOR scores. We show that the usage of morpho-syntactic information yields 3 BLEU points gain in the overall system.

Full Paper    

Bibliographic reference.  Köprü, Selçuk (2009): "Apptek Turkish-English machine translation system description for IWSLT 2009", In IWSLT-2009, 19-23.