9. Active Learning to Reduce Manual Validation Effort

Objective:

Reduce SME effort & time to validate entity matches by ~80%

to free up time for the SMEs - from having to manually label every match to just having to label those where the system is not absolutely certain about a match or no-match.

⁠

Active Learning

Auto-recommendation of sample entity matches that the model is not confident about and needs human feedback to learn

Create a UI to enable the SME to validate the matches presented to them recommended by the system.

Use this process iteratively to continue teaching the model to do better with each run.

Priority

Want to print your doc?
This is not the way.

Try clicking the ⋯ next to your doc name or using a keyboard shortcut (

CtrlP

) instead.