Self-Attention-based Data Augmentation Method for Text Classification.
Mehari Yohannes HailemariamSteven J. LyndenAkiyoshi MatonoToshiyuki AmagasaPublished in: ICMLC (2023)
Keyphrases
- preprocessing
- synthetic data
- text classification
- data sets
- database
- input data
- high dimensional data
- data cleaning
- prior information
- statistical methods
- test data
- bag of words
- labeled data
- image data
- prior knowledge
- data analysis
- training data
- semi supervised
- data sources
- data processing
- high dimensional
- semi supervised learning
- unlabeled data
- training samples
- pairwise
- similarity measure
- face recognition
- data mining
- databases