PHICON: Improving Generalization of Clinical Text De-identification Models via Data Augmentation.
Xiang YueShuang ZhouPublished in: CoRR (2020)
Keyphrases
- data sets
- data collection
- data processing
- prior knowledge
- accurate models
- experimental data
- neural network
- high quality
- data structure
- data analysis
- raw data
- synthetic data
- stored data
- text data
- learning models
- data quality
- original data
- database
- input data
- data points
- training data
- text documents
- statistical methods
- databases
- image data
- historical data
- learned models
- xml documents
- models built