Amazon Textract updates its Queries feature within Analyze Document API

Amazon Textract is a machine learning service that automatically extracts text, handwriting, and data from any document or image. We regularly improve the underlying machine learning models based on customer feedback to deliver better accuracy and latency. Today, we are pleased to announce quality enhancements to our Queries feature available via the AnalyzeDocument API. Queries allows customers to specify and extract information from documents in question-answer pairs. The latest Queries update improves data extraction accuracy across 14 new documents types such as certificates of insurance, coverage declarations, renters policy documents, payoff statements, and utility bills. Customers across industries like insurance, mortgage and real estate utilize these documents in their business processes and will automatically see the benefits of this update when they use Textract’s Queries extraction feature. We have also delivered enhancements to the underlying machine learning models resulting in reduced latency when calling AnalyzeDocument API with Queries feature enabled. This update will be available in US East (Ohio), US East (N. Virginia), US West (Northern California), US West (Oregon), Asia Pacific (Mumbai), Asia Pacific (Seoul), Asia Pacific (Singapore) , Asia Pacific (Sydney), Canada (Central), Europe (Frankfurt), Europe (Ireland), Europe (London), Europe (Paris), AWS GovCloud (US-East), and AWS GovCloud (US-West) Regions starting May 15th, 2023\. Click [here](https://aws.amazon.com/textract/) to get started with Analyze Document Queries and click [here](https://docs.aws.amazon.com/textract/latest/dg/bestqueries.html) for example queries for the document types that will see improved accuracy with this update.