Exploiting Synthetically Generated Data with Semi-Supervised Learning for Small and Imbalanced Datasets.
María Pérez-OrtizPeter TiñoRafal MantiukCésar Hervás-MartínezPublished in: CoRR (2019)
Keyphrases
- semi supervised learning
- labeled data
- training data
- unlabeled data
- imbalanced datasets
- data sets
- small number
- data analysis
- raw data
- learning algorithm
- class distribution
- test data
- semi supervised
- text classification
- supervised learning
- data distribution
- data points
- active learning
- original data
- prior knowledge
- training set