Insights from Russian second language readability classification: complexity-dependent training requirements, and feature evaluation of multiple categories.
Robert ReynoldsPublished in: BEA@NAACL-HLT (2016)
Keyphrases
- feature vectors
- training set
- classification accuracy
- training phase
- training samples
- supervised learning
- feature set
- feature extraction
- image classification
- training process
- feature weights
- automatically classify
- classification scheme
- labelled data
- automatic classification
- multi layer perceptron
- svm classifier
- feature analysis
- decision trees
- support vector machine svm
- machine learning algorithms
- image features
- computational complexity
- pattern classification
- pattern recognition
- classification systems
- machine learning
- discriminative features
- sufficient training data
- neural network
- hierarchical text classification
- svm classification
- classification algorithm
- model selection
- preprocessing
- training data
- data mining