Sciweavers

6 search results - page 2 / 2
» Combining the Lazy Label Evaluation with Focusing Techniques...
Sort
View
ACL
2006
13 years 6 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