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

Jump to bottom

smaller training percentage gets better perplexity? #4

Open

bhomass opened this issue Nov 24, 2019 · 0 comments

bhomass commented Nov 24, 2019

Hi Am I reading this correctly? Figure 1e shows for WEDTM, 20% training data performs markedly better than 80%. How does that make sense?

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