59 search results - page 9 / 12 » Minimum Error Rate Training in Statistical Machine Translati... |
COLT
2004
Springer
14 years 4 months ago
2004
Springer
The main goal of this paper is to prove inequalities on the reconstruction error for Kernel Principal Component Analysis. With respect to previous work on this topic, our contribu...
ICML
2009
IEEE
14 years 11 months ago
2009
IEEE
In this paper, we investigate a simple, mistakedriven learning algorithm for discriminative training of continuous density hidden Markov models (CD-HMMs). Most CD-HMMs for automat...
ICASSP
2011
IEEE
13 years 2 months ago
2011
IEEE
The context-independent deep belief network (DBN) hidden Markov model (HMM) hybrid architecture has recently achieved promising results for phone recognition. In this work, we pro...
ICML
2003
IEEE
14 years 11 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,...
EMNLP
2008
14 years 9 days ago
2008
BLEU is the de facto standard for evaluation and development of statistical machine translation systems. We describe three real-world situations involving comparisons between diff...