ACL
2006
13 years 5 months ago
2006
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
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...
IJCNN
2007
IEEE
13 years 10 months ago
2007
IEEE
— Efficient Training in a neural network plays a vital role in deciding the network architecture and the accuracy of these classifiers. Most popular local training algorithms t...