Exploring extreme parameter compression for pre-trained language models.
Benyou WangYuxin RenLifeng ShangXin JiangQun LiuPublished in: ICLR (2022)
Keyphrases
- language model
- pre trained
- language modeling
- training data
- n gram
- probabilistic model
- document retrieval
- language modelling
- speech recognition
- information retrieval
- test collection
- training examples
- query expansion
- retrieval model
- smoothing methods
- statistical language models
- control signals
- document ranking
- relevance model
- neural network
- generative model
- supervised learning