Compressing Large-Scale Transformer-Based Models: A Case Study on BERT.
Prakhar GaneshYao ChenXin LouMohammad Ali KhanYin YangHassan SajjadPreslav NakovDeming ChenMarianne WinslettPublished in: Trans. Assoc. Comput. Linguistics (2021)
Keyphrases
- fuzzy logic
- decision making
- genetic algorithm
- real world
- real life
- data sets
- test bed
- statistical models
- experimental data
- complex systems
- accurate models
- data compression
- neural network model
- machine learning algorithms
- probabilistic model
- hidden markov models
- prior knowledge
- multi agent systems
- training data
- information systems
- learning algorithm