Handling Class Imbalance when Detecting Dataset Mentions with Pre-trained Language Models.
Yousef YounesBrigitte MathiakPublished in: ICNLSP (2022)
Keyphrases
- language model
- class imbalance
- pre trained
- class distribution
- language modeling
- active learning
- training data
- probabilistic model
- speech recognition
- training examples
- cost sensitive
- information retrieval
- feature selection
- concept drift
- high dimensionality
- benchmark datasets
- test data
- test set
- pattern recognition
- face recognition
- prediction accuracy
- pairwise
- data streams
- training dataset