14 search results - page 2 / 3 » Minimum Error Rate Training by Sampling the Translation Latt... |
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
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...
EMNLP
2007
13 years 6 months ago
2007
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...
ICASSP
2008
IEEE
13 years 11 months ago
2008
IEEE
In this paper we investigate a discriminative approach to feature weighting for topic identification using minimum classification error (MCE) training. Our approach learns featu...
PRL
2007
13 years 4 months ago
2007
ct 7 Discriminative training for hidden Markov models (HMMs) has been a central theme in speech recognition research for many years. 8 One most popular technique is minimum classi...