quotation detection #506
Merged
quotation detection #506
Conversation
This file contains hidden or 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
bigabig
requested changes
Feb 26, 2025
bigabig
requested changes
Feb 28, 2025
bigabig
approved these changes
Feb 28, 2025
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Outdated suggestions cannot be applied.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 is a rather large PR that provides...
Quotation detection
Who says what to whom is automatically extracted from text using the quotect package.
Integrate quotect into the ray model worker
Send tokenized text to quotect model in ray, retrieve results and create span annotation as well as span groups to persist the predictions in the database.
Generic ML Jobs (Backend + Frontend)
As the model is rather heavy on compute, it is not added to our already too large pre-processing pipeline. Instead, this PR adds a new generic ML job that is used to run the quotation detection task on any unprocessed documents. If the user insists, it is also possible to delete any existing annotations and groups and re-compute (e.g. to use another quotation detection model on the same data)
Added a new page accessible by the drawer on the left to provide access to trigger ML automation features (currently only quotation detection):
Rendering span groups in the frontend UI
The document viewer and annotator now show span groups by numbering the span tags: