Skip to content

No space or unknown token in dataset dictionary, leading to training data corruption #1

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
Open
grappli opened this issue Aug 7, 2020 · 1 comment
Open

No space or unknown token in dataset dictionary, leading to training data corruption #1

grappli opened this issue Aug 7, 2020 · 1 comment

Comments

@grappli
Copy link

grappli commented Aug 7, 2020 •
edited
Loading

A major issue here is that spaces and unknown tokens aren't encoded as in the paper. As a result, inputs have all spaces removed. This is probably the cause of the reduced accuracy compared to the paper.
@grappli
Copy link
Author

grappli commented Aug 8, 2020

The first letter of each sentence is also cut off.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@grappli