Posted On: May 23, 2022

Amazon Comprehend is a natural language processing (NLP) service that uses machine learning (ML) to find insights and relationships like people, places, sentiments, and topics in unstructured text. You can use Amazon Comprehend ML capabilities to detect and redact personally identifiable information (PII) in customer emails, support tickets, product reviews, social media, and more. For example, you can analyze support tickets and knowledge articles to detect PII entities and redact the text before you index the documents in the search solution.

Previously, Amazon Comprehend supported 22 PII entities across multiple categories, including Financial (e.g., credit card number, bank account number), Personal (e.g., name, email, age), Technical Security (e.g., username, password), and National (e.g., social security number, passport number). Starting today, Amazon Comprehend PII will support 14 new entity types, with localized support for entities within the United States, Canada, United Kingdom, and India. Customers can now detect and redact 36 entities to protect sensitive data. Specifically, the new entities are:

  • United States (US Individual Tax Identification Number)
  • United Kingdom (National Insurance Number, UK Unique Taxpayer Reference Number, National Health Service Number)
  • Canada (Social Insurance Number, Canada Health Number)
  • India (Aadhaar Card, Permanent Account Number, NREGA, Voter Number)
  • Others (Vehicle Identification Number, SWIFT code, License Plate, International Bank Account Number)

To learn more and get started, visit the Amazon Comprehend product page or our documentation.