Document Understanding data not getting extracted

Help Activities
, ,
1

Hi All,

Need one small help in Document Understanding.

  1. I have two PDFs say A and B.
  2. From A and B I have to extract say field X
  3. From A the field is getting extracted but from B it is not getting extracted.
  4. Both the PDFs are identical in all aspects.
  5. I am using ML skill for this.

Thanks!!

2

Hi @Ritaman_Baral

Which ocr you are using

Can you share the screenshot

3

Omi Page OCR I am using

4

In datalabelling I found that the field is not getting greyed out

5

Hi @Ritaman_Baral ,

In such cases, we could try Debug or Check each output Stages with the help of Immediate Panel or Writing the Serialized text of the output to a text file.

Also, if it is possible we would like to also test the same case at our end if provided with the two sample documents.

When also mentioned identical in all aspects, we would also need to know How many documents were trained if using the DU Model or with ML Skill. We would like to know what was the ML Package used.

6

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