Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Why Transformer Decoder? #4

Closed
annanfree opened this issue Jun 6, 2024 · 1 comment
Closed

Why Transformer Decoder? #4

annanfree opened this issue Jun 6, 2024 · 1 comment
Labels
question Further information is requested

Comments

@annanfree
Copy link

why use transformer decoder for slots filling,why not something more simple. what's the reason or intuition for using the structure

@rafiepour
Copy link
Owner

Hi @annanfree,
The decoder needs to have a history of what it has already generated. The intuition was to use a network that had a memory, but did not have the limitation of LSTMs. Regular Transformer Decoder did not have a proper performance because of the alignment issue, and so , we introduced the aligned Transformer Decoder.
I highly suggest you to read the sciencedirect paper meticulously.

@rafiepour rafiepour changed the title why Why Transformer Decoder? Jun 19, 2024
@rafiepour rafiepour added the question Further information is requested label Jun 19, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants