Amazon Comprehend Introduces Custom Entities

Posted on: Nov 16, 2018

Amazon Comprehend is a natural language processing (NLP) service that uses machine learning to find insights and relationships in text. Starting today, customers can use the Custom Entities API to easily build models to extract custom entities (policy numbers, part codes, serial numbers, etc.) that are tailored to your organization’s need. Customers are now able to analyze the vast amount of unstructured data with the accuracy and entity coverage they need for their unique use cases.

No machine learning experience is required. To create a custom model, you simply need to provide a list of your entities and sample text that contains them. This process can be completed without writing a single line of code via the AWS management console. The feature is included in the AWS SDK for programmatic access. 

You can also learn more about this new feature in the documentation.