We address the problem of training the free parameters of a statistical machine translation system. We show significant improvements over a state-of-the-art minimum error rate tr...
When building rule-based machine translation systems, a considerable human effort is needed to code the transfer rules that are able to translate source-language sentences into gra...
In modern machine translation practice, a statistical phrasal or hierarchical translation system usually relies on a huge set of translation rules extracted from bi-lingual traini...
Translation rule extraction is an important issue in syntax-based Statistical Machine Translation (SMT). Recent studies show that rule coverage is one of the key factors affecting...