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

Adapt Huggingface predictor to PubMed #28

Open
pjuangph opened this issue May 6, 2021 · 1 comment
Open

Adapt Huggingface predictor to PubMed #28

pjuangph opened this issue May 6, 2021 · 1 comment
Assignees
Labels
enhancement New feature or request

Comments

@pjuangph
Copy link
Collaborator

pjuangph commented May 6, 2021

Part 1 David Tasks:

  1. write a downloader
  2. write an xml to panda file reader

Part 2 Paht Tasks:

  1. Adapt the petal-labeller with scibert to predicting the mesh terms labels. Predicting multiple labels may be tricky but should be investigated.

Paht and David Tasks. Alex too, why not.

  1. Look up machine learning models that can do multiple classifications in NLP or images. Something we could use to classify multiple meshterms.

Purpose of this task is to use more data and from that decide if Bert is the best way to go and if we need to improve Bert, how accurate can we make the prediction? The dataset will be more than what we currently have and this is a great benchmark for predicting the Labels from Colleen and Alex

@pjuangph pjuangph added the enhancement New feature or request label May 6, 2021
@pjuangph pjuangph changed the title Adapt Huggingface predictor to Alex's dataset part 1 Adapt Huggingface predictor to Alex's dataset May 6, 2021
@pjuangph
Copy link
Collaborator Author

Task 1 is complete. Thanks David https://github.com/nasa-petal/PubMed

@pjuangph pjuangph changed the title Adapt Huggingface predictor to Alex's dataset Adapt Huggingface predictor to PubMed May 27, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

3 participants