An Empirical Study of Leveraging Knowledge Distillation for Compressing Multilingual Neural Machine Translation Models
3033Knowledge Triples
| Source Entity | Relationship | Target Entity |
|---|---|---|
|
Adapters
Method |
usedIn |
KnowledgeDistillation
Method |
|
Deeper Models
Method |
usedIn |
KnowledgeDistillation
Method |
|
KnowledgeDistillation
Method |
appliesTo | |
|
KnowledgeDistillation
Method |
appliesTo |
Neural Machine Translation
Method |
| includes | ||
|
Multistage Training
Method |
usedIn |
KnowledgeDistillation
Method |
|
Parameter Sharing
OtherEntity |
usedIn |
KnowledgeDistillation
Method |
|
Shallower Models
Method |
usedIn |
KnowledgeDistillation
Method |