Unable to Train my Extractor in Document Understanding Workflow

Help Document Understanding
, ,
1

Hey
I’m working on a process in which I’ve created a workflow for extracting data from a form placed at some location. Everything’s working fine but the machine isn’t learning
In every attempt I manually validate the data in the validation station and after every run, the workflow (extractor) makes the same mistake that I’ve rendered earlier. Means, that the machine isn’t learning

I’ve loaded the taxonomy
then digitized the document using omnipage OCR.
classified it using keyword based classifier
then extracting data using Form Extractor
then the validation station appears where I manually validate the data everytime
and then the trainer comes in. I’m currently using train classifier scope in which I’ve used keyword based classifier trainer

and every time in the validation station, I’ve to re-render all the changes that I’ve already fixed. The machine isn’t learning from experiences even though I’ve used the trainer

Can anyone suggest me how to train my bot so that in every attempt the machine learns from the input I fix manually.
It’ll be really appreciated.

2

Hello @raheelferoze!

It seems that you have trouble getting an answer to your question in the first 24 hours.
Let us give you a few hints and helpful links.

First, make sure you browsed through our Forum FAQ Beginner’s Guide. It will teach you what should be included in your topic.

You can check out some of our resources directly, see below:

  1. Always search first. It is the best way to quickly find your answer. Check out the image icon for that.
    Clicking the options button will let you set more specific topic search filters, i.e. only the ones with a solution.

  2. Topic that contains most common solutions with example project files can be found here.

  3. Read our official documentation where you can find a lot of information and instructions about each of our products:

  4. Watch the videos on our official YouTube channel for more visual tutorials.

  5. Meet us and our users on our Community Slack and ask your question there.

Hopefully this will let you easily find the solution/information you need. Once you have it, we would be happy if you could share your findings here and mark it as a solution. This will help other users find it in the future.

Thank you for helping us build our UiPath Community!

Cheers from your friendly
Forum_Staff

3

The Form Extractor activity has no associated Trainer activity and thus cannot be trained to improve after each validation. From your description I understand that you are using Keyword Based Classifier Trainer, which improves the classification part, not the extraction.

4

@tudor.serban Yeah, I’m using “keyword Based Classifier”. So, is there any way through which I can retrain my extractor? I know there must be a way to do that while using form Extractor / Intelligent Form Extractor.
I did looked into the ML extractor but the machine learning extractor can only be used for invoices or receipts, that’s why I’m using Form Extractor / Intelligent Form Extractor as I’m working with some documents of different format.
So, Is there any way / suggestion about what can I do?

5

neither Form Extractor nor Intelligent Form Extractor are capable of learning. They are purely rule based and configuration driven. You will need to adjust an existing template or create a new one.

In FE and IFE you can have multiple templates for the same document type, for instance if you have 2 very different versions of the same form. Also please take a look at the new anchor based functionality just released for FE and IFE which allows a bit more flexibility in defining fields.

1 Like