1377 search results - page 68 / 276 » Statistical Machine Reordering |
110
Voted
ICML
2003
IEEE
16 years 3 months ago
2003
IEEE
When the goal is to achieve the best correct classification rate, cross entropy and mean squared error are typical cost functions used to optimize classifier performance. However,...
136
Voted
ICML
2001
IEEE
16 years 3 months ago
2001
IEEE
Direct policy search is a practical way to solve reinforcement learning problems involving continuous state and action spaces. The goal becomes finding policy parameters that maxi...
129
Voted
COLT
1997
Springer
15 years 6 months ago
1997
Springer
Abstract. We propose a convex optimization approach to solving the nonparametric regression estimation problem when the underlying regression function is Lipschitz continuous. This...
107
Voted
CMMR
2004
Springer
15 years 7 months ago
2004
Springer
Abstract. The paper concerns the use of multiple viewpoint representation schemes for prediction with statistical models of monophonic music. We present an experimental comparison ...
99
Voted
NAACL
2003
15 years 3 months ago
2003
Following the recent adoption by the machine translation community of automatic evaluation using the BLEU/NIST scoring process, we conduct an in-depth study of a similar idea for ...