Sciweavers

ACL
2006
14 years 1 months ago
Minimum Risk Annealing for Training Log-Linear Models
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...
David A. Smith, Jason Eisner
EMNLP
2008
14 years 1 months ago
Lattice-based Minimum Error Rate Training for Statistical Machine Translation
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...
Wolfgang Macherey, Franz Josef Och, Ignacio Thayer...
IJCNN
2007
IEEE
14 years 6 months ago
TRUST-TECH Based Neural Network Training
— 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...
Hsiao-Dong Chiang, Chandan K. Reddy