Investigating an Approach for Low Resource Language Dataset Creation, Curation and Classification: Setswana and Sepedi.
Vukosi MarivateTshephisho SefaraVongani ChabalalaKeamogetswe MakhayaTumisho B. MokgonyaneRethabile MokoenaAbiodun ModupePublished in: RAIL (2020)
Keyphrases
- classification accuracy
- benchmark datasets
- pattern recognition
- feature vectors
- decision trees
- pattern classification
- automatic classification
- uci datasets
- classification systems
- object classification
- model selection
- supervised learning
- neural network
- classification models
- classification scheme
- support vector machine svm
- feature set
- text classification
- data mining
- support vector machine
- feature space
- preprocessing
- machine learning
- support vector
- object recognition
- fold cross validation
- resource constraints
- training dataset
- feature selection
- face recognition
- natural language
- programming language
- language learning
- classification method
- resource allocation
- decision rules
- training set
- natural language processing