Patient Knowledge Distillation for BERT Model Compression.

Siqi Sun Yu Cheng Zhe Gan Jingjing Liu

Published in: EMNLP/IJCNLP (1) (2019)

Keyphrases

computational model
formal model
statistical model
knowledge representation
knowledge discovery
theoretical analysis
mathematical model
management system
data sets
prior knowledge
domain experts
multiscale
information systems
experimental data
conceptual model
expert knowledge
neural network