Connecting Pre-trained Language Model and Downstream Task via Properties of Representation.
Chenwei WuHolden LeeRong GePublished in: NeurIPS (2023)
Keyphrases
- language model
- pre trained
- language modeling
- n gram
- probabilistic model
- document retrieval
- retrieval model
- information retrieval
- test collection
- speech recognition
- ad hoc information retrieval
- mixture model
- context sensitive
- query expansion
- translation model
- image representation
- smoothing methods
- training data
- feature extraction