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...
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...
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...
Abstract. Professional translators of technical documents often use Translation Memory (TM) systems in order to capitalize on the repetitions frequently observed in these documents...
We present a method to transliterate names in the framework of end-to-end statistical machine translation. The system is trained to learn when to transliterate. For Arabic to Engl...