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: CoRR (2020)
Keyphrases
- database
- pattern recognition
- benchmark datasets
- support vector machine
- classification accuracy
- preprocessing
- automatic classification
- classification method
- image classification
- classification scheme
- pattern classification
- programming language
- text classification
- classification rules
- object classification
- uci datasets
- classification algorithm
- creation process
- support vector machine svm
- feature space
- natural language
- support vector
- decision trees
- machine learning algorithms
- feature set
- feature vectors
- high dimensional
- object recognition
- classification rate
- training dataset
- classification systems