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...
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...
Lattice decoding in statistical machine translation (SMT) is useful in speech translation and in the translation of German because it can handle input ambiguities such as speech r...
This paper presents MISTRAL, an open source statistical machine translation decoder dedicated to spoken language translation. While typical machine translation systems take a writ...
Minimum Error Rate Training (MERT) is an effective means to estimate the feature function weights of a linear model such that an automated evaluation criterion for measuring syste...
Wolfgang Macherey, Franz Josef Och, Ignacio Thayer...