Hierarchical phrase-based models provide a powerful mechanism to capture non-local phrase reorderings for statistical machine translation (SMT). However, many phrase reorderings a...
We describe an approach to improve Statistical Machine Translation (SMT) performance using multi-lingual, parallel, sentence-aligned corpora in several bridge languages. Our appro...
—We describe the design of an autonomous agent that can teach itself how to translate from a foreign language, by first assembling its own training set, then using it to improve...
We address the problem of smoothing translation probabilities in a bilingual N-grambased statistical machine translation system. It is proposed to project the bilingual tuples ont...
Minimum Error Rate Training is the algorithm for log-linear model parameter training most used in state-of-the-art Statistical Machine Translation systems. In its original formula...