A New Feature Selection Score for Multinomial Naive Bayes Text Classification Based on KL-Divergence.
Karl-Michael SchneiderPublished in: ACL (Poster and Demonstration) (2004)
Keyphrases
- text classification
- kl divergence
- feature selection
- kullback leibler divergence
- information theoretic
- mutual information
- text categorization
- mahalanobis distance
- gaussian mixture
- bag of words
- machine learning
- gaussian distribution
- labeled data
- n gram
- exponential family
- text documents
- unsupervised learning
- posterior distribution
- probability density
- support vector
- feature space
- knn
- text mining
- feature set
- multi label
- feature extraction
- probabilistic latent semantic analysis
- cross lingual
- information theory
- gaussian mixture model
- dissimilarity measure
- dimensionality reduction
- multi task
- noise model
- scoring function
- image segmentation
- probabilistic model
- em algorithm