Latin Etymologies as Features on BNC Text Categorization.
Alex Chengyu FangWanyin LiNancy IdePublished in: PACLIC (2009)
Keyphrases
- text categorization
- feature generation
- information gain
- feature weighting
- feature selection
- text classification
- knn
- feature reduction
- k nearest neighbor
- multi label
- feature set
- automated text categorization
- text classifiers
- reuters corpus
- text documents
- automatic text categorization
- document classification
- linear svm
- naive bayes
- training documents
- feature selections
- neural network
- semi supervised learning
- pairwise
- term frequency
- image classification
- image features
- feature vectors
- feature space
- machine learning
- model selection
- bayesian network classifiers
- dimensionality reduction
- prior knowledge