On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency.
Seoyeon ParkCornelia CarageaPublished in: ACL (1) (2022)
Keyphrases
- language model
- pre trained
- language modeling
- training data
- probabilistic model
- document retrieval
- n gram
- speech recognition
- training examples
- test collection
- query expansion
- control signals
- retrieval model
- information retrieval
- training set
- support vector
- relevance model
- language modelling
- visual attention
- language models for information retrieval
- neural network
- statistical language models
- multi modal
- smoothing methods