On feature selection in maximum entropy approach to statistical concept-based speech-to-speech translation.

Liang Gu Yuqing Gao

Published in: IWSLT (2004)

Keyphrases

maximum entropy
feature selection
speech recognition
maximum entropy principle
text categorization
mutual information
conditional random fields
class conditional
machine learning
model selection
named entity recognition
markov models
multi class
em algorithm
machine translation