Patient Knowledge Distillation for BERT Model Compression.
Siqi SunYu ChengZhe GanJingjing LiuPublished in: CoRR (2019)
Keyphrases
- computational model
- prior knowledge
- mathematical model
- conceptual model
- probabilistic model
- domain knowledge
- statistical model
- multiresolution
- video sequences
- probability distribution
- experimental data
- knowledge base
- information systems
- theoretical framework
- data compression
- em algorithm
- expert knowledge
- semantic models
- parameter estimation
- knowledge based systems
- data mining
- expert systems
- similarity measure
- machine learning