Getting started with Amazon Comprehend - Amazon Comprehend

Getting started with Amazon Comprehend

The following exercise uses the Amazon Comprehend console to create and run an asynchronous entity detection job. This exercise assumes that you are familiar with Amazon Simple Storage Service (Amazon S3). For a simpler example, see Real-time analysis using the built-in models.

To create a entity detection job

  1. Sign in to the console.

  2. From the left menu, choose Analysis Jobs and then choose Create job.

  3. Under Job settings, give the job a name. The name must be unique within the region and account.

  4. For Analysis Type, choose Entities.

  5. For Language, choose the language of the input documents.

  6. Under Input data, for Data source, choose Example documents. The console sets S3 location to be the folder containing the public samples.

  7. Under Output data, in S3 location, paste the URL or folder location in Amazon S3 for the output files.

  8. Under Access permissions section, select Create an IAM role. The console creates a new IAM role with the proper permissions for Amazon Comprehend to access the input and output buckets.

  9. When you have finished filling out the form, choose Create job to create and start the topic detection job.

    The new job appears in the job list with the status field showing the status of the job. The field can be IN_PROGRESS for a job that is processing, COMPLETED for a job that has finished successfully, and FAILED for a job that has an error.

  10. Choose the job to open the Job details panel.

  11. Under Output, in Output data location choose the link to open the Amazon S3 console.

  12. In the Amazon S3 console, choose Download and save the output.tar.gz file.

  13. Decompress the file and save it as a Json file.

  14. See Entities for a description of the entity types and the fields for each detected entity.