One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers
33797Knowledge Triples
| Source Entity | Relationship | Target Entity |
|---|---|---|
|
KnowledgeDistillation
Method |
implements |
MTBERT
Method |
|
MTBERT
Method |
uses |
Multi Teacher Co finetuning
Method |
|
MTBERT
Method |
uses | |
|
MTBERT
Method |
uses |
Multi Teacher Hidden Loss
Metric |