Och's (2003) minimum error rate training (MERT) procedure is the most commonly used method for training feature weights in statistical machine translation (SMT) models. The u...
This paper presents MISTRAL, an open source statistical machine translation decoder dedicated to spoken language translation. While typical machine translation systems take a writ...
Statistical machine translation (SMT) models require bilingual corpora for training, and these corpora are often multilingual with parallel text in multiple languages simultaneous...
This paper considers a scenario when we are given almost perfect knowledge about bilingual terminology in terms of a test corpus in Statistical Machine Translation (SMT). When the...
We present a new phrase-based conditional exponential family translation model for statistical machine translation. The model operates on a feature representation in which sentenc...