Amazon Comprehend is now Natively Integrated with Datasaur

You can now connect with Amazon Comprehend to predict labels within the interface.
Post Header Image
July 5, 2023
Published on
July 5, 2023
July 5, 2023
Post Detail Image

With our latest update, we have added a new provider to the ML Assisted extension: Amazon Comprehend. You now able to connect Comprehend natively in Datasaur! Amazon Comprehend is an advanced natural language processing (NLP) service by AWS that enables you to gain valuable insights from text data effortlessly. Now, imagine harnessing the power of Amazon Comprehend directly within our intuitive labeling platform, streamlining the way you annotate data. With ML Assisted Labeling and Amazon Comprehend, you can unlock the full potential of your data annotation workflow, driving innovation and leveraging the intelligent capabilities of Comprehend for enhanced precision and speed.

Connect Natively

First, you have to have an AWS account and enable a new role in your Identity and Access Management (IAM) for the AWS Comprehend permission. This will allow your Amazon to connect with any third-party app if needed, like Datasaur. You can now copy the Account ID and External ID that you get from our ML Assisted Extension to allow the connection for the new role permission.

Amazon Identity and Access management Role form

After that, don’t forget to add Policies for your permission, these will allow your model in comprehend to do Document Classification. You can use this policy:

  "Version": "2012-10-17",
  "Statement": [
      "Sid": "VisualEditor0",
      "Effect": "Allow",
      "Action": "comprehend:ClassifyDocument",
      "Resource": "*"

After you add your permission you can name the Role Name and then create it! Now all you need to do is to get your Role ARN and the Endpoint ARN for your model to be accessed by Datasaur and input it back to the ML Assisted extension with the Amazon Comprehend provider.

Identity and Access Management Role Summary (Role ARN)

Amazon Comprehend Model Endpoint Detail (Endpoint ARN)

Start your label-assisted process with Datasaur

Final Result after generated by Amazon Comprehend model

Here is the example of the use of Amazon Comprehend provider in ML Assisted! You can see the Target Question which is Question 1 is filled by the model from Amazon Comprehend as recommendations so the reviewer can review it again. Take the leap today and witness the game-changing impact firsthand!

Get started to make your labeling faster!

You can now begin a free two week trial with Datasaur. Contact us at if you have any questions or would like to have an onboarding call. We will be happy to assist you with any questions you may have and help you get up and running with this powerful tool and new feature.

Happy Labeling!

No items found.