7 search results - page 2 / 2 » Fluency Constraints for Minimum Bayes-Risk Decoding of Stati... |
EMNLP
2010
13 years 3 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...
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...