Active Learning to Select Unlabeled Examples with Effective Features for Document Classification.
Minoru SasakiPublished in: CICLing (2) (2019)
Keyphrases
- document classification
- active learning
- unlabeled examples
- training examples
- labeled examples
- labeled data
- semi supervised
- semi supervised learning
- text classification
- feature set
- text documents
- text categorization
- co occurrence
- unlabeled data
- classification algorithm
- feature space
- feature selection
- keywords
- web documents
- k nearest neighbor
- machine learning
- text mining
- object recognition
- support vector
- feature vectors
- natural language processing
- feature extraction
- support vector machine