WeLT: Improving Biomedical Fine-tuned Pre-trained Language Models with Cost-sensitive Learning.
Ghadeer MobasherWolfgang MllerOlga KrebsMichael GertzPublished in: BioNLP@ACL (2023)
Keyphrases
- language model
- cost sensitive learning
- pre trained
- fine tuned
- cost sensitive
- document retrieval
- probabilistic model
- speech recognition
- fine tuning
- misclassification costs
- probability estimation
- class imbalance
- missing values
- query expansion
- training examples
- active learning
- training data
- information retrieval
- domain specific
- test collection
- machine learning
- class distribution
- decision trees
- information extraction
- multi class
- classification accuracy
- training set
- support vector
- learning algorithm