Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback
37799Knowledge Triples
| Source Entity | Relationship | Target Entity |
|---|---|---|
|
Deployment data
Material |
contains |
Human Feedback
Material |
|
Human Feedback
Material |
informs |
Model guiding
Method |
|
Human Feedback
Material |
informs |
Rejection sampling
Method |
|
Human Feedback
Material |
informs |
Reward based learning
Method |
|
Human Feedback
Material |
informs |
Supervised Learning
Method |
|
Internet retrieval
Method |
uses |
Human Feedback
Material |