Save extraction data in validation station

Help Document Understanding
1

Hi All,

I think asked previously too but I am still unable to figure this out…

  1. validation station comes up and
  2. I indicate the values and the confidence turns to 100%
  3. I save extracted values

However, in the next run,it asks me to indicate same value again ! The confidence level has fallen below. So,
1.what does Save extraction actually do ?
2. What is the purpose of Learning.json ?
3. how can I prevent the validation station from asking for same values to be validated once it is done.

2

Validation Station is only a UI. It does not automatically trigger the retraining loop.
The retraining loop is triggered by using the Train Extractors Scope activity.
The ML Extractor does not currently publish a training activity - this feature will be available later in the on-prem ML options.

3

Thanks Iona. You had answered this in Insider. Sorry I didn’t close this question.

1 Like
4

This topic was automatically closed 3 days after the last reply. New replies are no longer allowed.