Skip to main content
  • Home
  • Forums
  • Developers Forum
  • Document Automation training validation feedback does not prevent fields not present on page from being extracted as incorrect values.

When I am validating data extracted from documents, I’m noticing that when a field is not present on one document, it is sometimes being extracted as as another incorrect value on the page. In the learning instance setup, the field is marked as optional and the confidence is set at 80%. I submit validation feedback by removing the mapping to the value, but each time I process a new document, it extracts the same incorrect data point. I have the same issue with tables that are being extracted for some documents for which the tables are not needed. Even after removing the mappings, the tables are extracted again when processing additional documents. 

 

Is there a solution for this issue or a best practice for solving this problem? 

@schehade have you tried using Advanced Training Settings while mapping values and validating documents?

 

 

@ShreyaKumar Thanks for your response. I’ve looked at the advanced training settings, but I’m not sure how they can help solve my problem. Are there advanced training settings for fields other than tables? 

 

My main issue is that I have optional fields that are populated with the wrong data when the data isn’t located on the page. For example, I have many formats of invoices, and some have a due date listed on the page while others do not. For the invoices with no due date, the invoice number ends up being extracted and placed in the due date field. Even when I remove the mapping and submit the validation feedback, I end up having to validate that field every time that invoice type is processed. Any ideas? 

Reply


Terms & ConditionsCookie settings