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.

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

Fine-Tune BERT on I2B2 #15

Open
boyleconnor opened this issue Sep 3, 2021 · 1 comment
Open

Fine-Tune BERT on I2B2 #15

boyleconnor opened this issue Sep 3, 2021 · 1 comment
Assignees
@boyleconnor
Labels
Enhancement New feature or request Priority: Low This issue can be kept on the back burner for now

Comments

@boyleconnor
Copy link
Collaborator

Describe the solution you'd like

Fine-tune BERT for NER on I2B2, then publish it to Transformers.

This is probably not the right repo for this issue.
@boyleconnor boyleconnor added the Enhancement New feature or request label Sep 3, 2021
@boyleconnor boyleconnor self-assigned this Sep 3, 2021
@tschaffter tschaffter added the Priority: Low This issue can be kept on the back burner for now label Sep 30, 2021
@boyleconnor
Copy link
Collaborator Author

Mostly done, using this Colab notebook and committed to HuggingFace here.

There was an issue with the training where I think the last chunk of text can get excluded This will negatively impact performance somewhat. I will fix that and re-train.

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

@boyleconnor boyleconnor

Labels
Enhancement New feature or request Priority: Low This issue can be kept on the back burner for now
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@tschaffter @boyleconnor