Document understand field extraction issue

Good morning,

I am using DU to extract the particular fields from PDF. I can able to get all the fields in some pdfs. And for some PDFs i could not able to extract the data. The data is not extracted. Can any one help me out how to train the extractor.

I am using Form extractor here


Form Extractor will work for Structured data only. If it is unstructured data then try with RegEx Based/Intelligent Form/ML Extractor

Hi lakshman,

This is structured data only. And we have only one template.

The reason why we have choosen DU is we have used regex to extract from read pdf text.

The output and position of the read pdf text is different for different clients. So we have choosen this DU.

Anyhow I have used regex extractor it not working . In form based extractor some fields are seems to be correct.

In some of the documents the fields are not extracted or partially extracted.

Can you please tell me how to sort this out?