59 search results - page 1 / 12 » Minimum Error Rate Training in Statistical Machine Translati... |
COLING
2008
13 years 6 months ago
2008
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...
EMNLP
2008
13 years 6 months ago
2008
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...
ACL
2003
13 years 6 months ago
2003
Often, the training procedure for statistical machine translation models is based on maximum likelihood or related criteria. A general problem of this approach is that there is on...
ACL
2009
13 years 2 months ago
2009
Minimum Error Rate Training (MERT) and Minimum Bayes-Risk (MBR) decoding are used in most current state-of-theart Statistical Machine Translation (SMT) systems. The algorithms wer...
EMNLP
2010
13 years 2 months ago
2010
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...