Login / Signup
Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight Tuning.
Apoorv Dankar
Adeem Jassani
Kartikaeya Kumar
Published in:
CoRR (2023)
Keyphrases
</>
loss function
statistical models
machine learning methods
machine learning algorithms
logistic regression
learning models
information retrieval
support vector
pairwise
supervised learning
model selection
cross validation
boosting algorithms