Performance evaluation of HMM-based style classification with a small amount of training data.
Makoto TachibanaKeigo KawashimaJunichi YamagishiTakao KobayashiPublished in: INTERSPEECH (2007)
Keyphrases
- training data
- classification accuracy
- decision trees
- classification models
- training set
- supervised learning
- pattern recognition
- class labels
- support vector machine
- training process
- pattern classification
- training samples
- learning algorithm
- training dataset
- classification method
- domain knowledge
- small number
- small sample
- classification process
- unsupervised learning
- hidden markov models
- automatic classification
- classification algorithm
- machine learning
- feature extraction
- support vector
- prior knowledge
- test set
- training examples
- text classification
- feature vectors
- test data
- benchmark datasets
- cost sensitive
- feature selection
- support vector machine svm
- classification rate
- text categorization
- model selection
- sufficient training data