Improving n-gram probability estimates by compound-head clustering.

Joris Pelemans Kris Demuynck Hugo Van hamme Patrick Wambacq

Published in: ICASSP (2015)

Keyphrases

n gram
probability estimates
language model
text classification
cost sensitive
naive bayes
clustering algorithm
decision trees
probability estimation
k means
unsupervised learning
posterior probability
misclassification costs
web documents
classification accuracy
classification models
roc curve