Training without training data: Improving the generalizability of automated medical abbreviation disambiguation.
Marta SkretaAryan ArbabiJixuan WangMichael BrudnoPublished in: ML4H@NeurIPS (2019)
Keyphrases
- training data
- training process
- training set
- training examples
- supervised learning
- training samples
- medical students
- test set
- training dataset
- labeled training data
- labelled data
- training patterns
- training and test data
- natural language processing
- co occurrence
- semi automated
- classification accuracy
- medical diagnosis
- training and testing data
- context sensitive
- labeled data for training
- training corpus
- annotation effort
- data sets
- training algorithm
- natural language
- labeled data
- sufficient training data
- medical data
- word sense disambiguation
- unlabeled data
- artificial neural networks
- decision trees
- machine learning
- neural network