Untranslated words still constitute a major problem for Statistical Machine Translation (SMT), and current SMT systems are limited by the quantity of parallel training texts. Augm...
This paper proposes to use monolingual collocations to improve Statistical Machine Translation (SMT). We make use of the collocation probabilities, which are estimated from monoli...
tra Statistical machine translation systems are usually trained on large amounts of bilingual text and monolingual text. In this paper, we propose a method to perform domain adapta...