OpenAdapt
OpenAdapt copied to clipboard
Investigate Improving Redaction
Feature request
e.g. Presidio, others?
We need a (VERY LIGHTWEIGHT) evaluation framework for different commercial and non-commercial redaction APIs/libraries.
We want to generate plots of various accuracy measures for each one.
Motivation
https://github.com/OpenAdaptAI/OpenAdapt/pull/418
My next follow-up is that: Since there are not any other Redaction tool that are working effectively. How could we investigate improving redaction. Should we rename this Issue to investigation improving redaction in Presidio instead ?
Shall we close this @abrichr as completed?
@KrishPatel13 I think for this to be considered completed we will need to implement automated tests which evaluate each provider on a dataset we curate.
This is low priority for now.