Bilingual n{gram statistical machine translation

This paper describes a statistical machine trans-lation system that uses a translation model which is based on bilingual n-grams. When this translation model is log-linearly combined with four specific feature functions, state of the art translations are achieved for Spanish-to-English and English-to-Spanish translation tasks. Some specific results obtained for the EPPS (Euro-pean Parliament Plenary Sessions) data are pre-sented and discussed. Finally, future research issues are depicted.