342 search results - page 6 / 69 » Refining Generative Language Models using Discriminative Lea... |
116
Voted
ACL
2010
15 years 7 days ago
2010
Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to i...
104
Voted
EMNLP
2010
15 years 6 days ago
2010
This paper examines tagging models for spontaneous English speech transcripts. We analyze the performance of state-of-the-art tagging models, either generative or discriminative, ...
122
Voted
ICASSP
2010
IEEE
15 years 2 months ago
2010
IEEE
We present a novel discriminative training algorithm for n-gram language models for use in large vocabulary continuous speech recognition. The algorithm uses large margin estimati...
110
Voted
CVPR
2007
IEEE
16 years 4 months ago
2007
IEEE
A major shortcoming of discriminative recognition and detection methods is their noise sensitivity, both during training and recognition. This may lead to very sensitive and britt...
109
click to vote
NIPS
2000
15 years 3 months ago
2000
The product of experts learning procedure [1] can discover a set of stochastic binary features that constitute a non-linear generative model of handwritten images of digits. The q...