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

Significant number of "unks" even when using subword units #524

Open
neubig opened this issue Aug 20, 2018 · 1 comment
Open

Significant number of "unks" even when using subword units #524

neubig opened this issue Aug 20, 2018 · 1 comment

Comments

@neubig
Copy link
Contributor

neubig commented Aug 20, 2018

I've noticed in several of my experiments that xnmt is generating "s" even when using sentencepiece, which is strange. This issue is a reminder to myself to check why this is happening and see if it's a bug in xnmt itself, or just in my experimental setup.

@philip30
Copy link
Contributor

This actually does not happen to me.

I use sentpiece but I didn't use the xnmt preprocessing script to prepare the data.

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

No branches or pull requests

2 participants