Extended pre-processing pipeline for text classification: On the role of meta-feature representations, sparsification and selective sampling.
Washington CunhaSérgio D. CanutoFelipe ViegasThiago SallesChristian GomesVítor MangaraviteElaine ResendeThierson RosaMarcos André GonçalvesLeonardo RochaPublished in: Inf. Process. Manag. (2020)
Keyphrases
- feature representations
- selective sampling
- text classification
- processing pipeline
- feature selection
- active learning
- feature representation
- image representation
- random sampling
- generative model
- text categorization
- text mining
- labeled data
- low level features
- machine learning
- classifier ensemble
- unlabeled data
- multi label
- image classification
- decision trees
- object recognition
- face recognition
- knn