search

open-metadata / OpenMetadata

OpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.
https://open-metadata.org
Apache License 2.0
5.67k stars 1.07k forks source link

Change Of NLP Model for Auto Tagging PII #15175

Open sharmalokeshk opened 9 months ago

sharmalokeshk commented 9 months ago

Every Country has different Rules and Regulations. So accordingly they have different PII fields. Such as in INDIA we have aadhaar and PAN. So your model will not TAG accordingly.

So, We can add our own NLP model which is trained and tested for our country's data. PII data tagging results will be more accurate.

If you can provide Steps to make changes in your codebase where the NLP model code is written and how we can integrate our model that will be helpful.

Check if any alternatives are possible on your side.

asaadkhaja99 commented 2 months ago

Can I contribute to this issue?