CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade.
Lei LiYankai LinDeli ChenShuhuai RenPeng LiJie ZhouXu SunPublished in: EMNLP (Findings) (2021)
Keyphrases
- language model
- probabilistic model
- statistical language models
- language modelling
- n gram
- language modeling
- pre trained
- information retrieval
- language models for information retrieval
- smoothing methods
- document retrieval
- translation model
- relevance model
- learning algorithm
- test collection
- bayesian networks
- statistical language modeling
- retrieval model
- pseudo relevance feedback
- data sets
- query expansion
- decision trees
- machine learning