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

Moves LayerNorm to output of the Encoder's sub-layers #47

Open
wants to merge 1 commit into
base: master
Choose a base branch
from

Conversation

patrickgadd
Copy link

Hi there,

As explained in #46, I believe that there is a minor lack of correspondence between the implementation and what's written in the paper ("Context-Aware Learning to Rank with Self-Attention") when it comes to the Transformer architecture.

Sadly I can't say whether this in practice affects performance, as I'm attempting to utilize this work for something entirely different.
However, it looks like that with the fix, learning is a tad more stable.

At any rate, thank you once again for this work and publishing it!

@PrzemekPobrotyn
Copy link
Contributor

please see my response in #46

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants