New multi-label synthetic train data biomedBERT #81
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This model supports a much wider 18 different classes with a 95.6% F1 score on LLM generated multilabel data
RichJackson
reviewed
Dec 17, 2024
RichJackson
approved these changes
Dec 17, 2024
paluchasz
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR introduces a new improved Transformer NER model. The model is multi-label and has been trained on LLM annotated data. It can support 18 different classes and has a mean F1 score of 95.6% on a held out LLM annotated test set. It has been trained on over 7000 documents which includes a total of 295822 samples.
The model is added to the model pack with an example config but is not enabled by default, as it is still experimental and further work should be done to investigate/improve the quality of the data it was trained on.