UPC’s Bilingual N-gram Translation System

This paper describes the UPC’s bilingual n-gram approach to statistical machine translation, which implements the log-linear combination of a bilingual n-gram translation model with six additional feature functions. A brief description of the complete system is presented and special attention is devoted to the novel features and reordering strategies that have been recently implemented. Translation results for the Spanish-to-English and English-to-Spanish tasks considered during the TC-STAR’s second evaluation campaign are presented and discussed. Finally, improvements achieved in translation accuracy with respect to the previous year’s system are also evaluated and discussed