Multi-pretraining for Large-scale Text Classification.
Kang-Min KimBumsu HyeonYeachan KimJun-Hyung ParkSangKeun LeePublished in: EMNLP (Findings) (2020)
Keyphrases
- text classification
- text categorization
- machine learning
- bag of words
- feature selection
- text mining
- sentiment analysis
- text documents
- neural network
- text data
- naive bayes
- real world
- multi label
- website
- document classification
- text classifiers
- k nearest neighbor
- data processing
- real life
- small scale
- databases
- data cleaning