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.

Sign up for GitHub

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

what is Li in paper? #10

Open

trankha1655 opened this issue Dec 18, 2021 · 1 comment

trankha1655 commented Dec 18, 2021

l(y, v) is NLLLoss

in your paper: "You first convert the list of negative log likelihood values into a probability distribution":

but in your code:

it is softmax( 1/loss) not softmax(-loss)?
Can you explain me?

Author

trankha1655 commented Dec 18, 2021

It's same with Di (probability distribution of edit-distance between 10 candidates and target)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment