EMNLP
2009
13 years 2 months ago
2009
Minimum error rate training (MERT) involves choosing parameter values for a machine translation (MT) system that maximize performance on a tuning set as measured by an automatic e...
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...
MT
2010
13 years 2 months ago
2010
In Minimum Error Rate Training (MERT), BLEU is often used as the error function, despite the fact that it has been shown to have a lower correlation with human judgment than other...
ACL
2008
13 years 6 months ago
2008
Current re-ranking algorithms for machine translation rely on log-linear models, which have the potential problem of underfitting the training data. We present BoostedMERT, a nove...