Amazon Translate Documentation

Neural Network-Based

Amazon Translate is designed to use deep learning techniques to produce translation. The neural machine translation system is built on a neural network that is designed to take into account the context of the source sentence as well as the translation it has generated so far.

Customized Machine Translation

Using Active Custom Translation (ACT), Amazon Translate enables you to bring your data (“parallel data”) to Amazon Translate to help customize the machine translated output to suit your needs. You can update your parallel data to keep your customized translation up to date.

Named Entity Translation Customization

Using Custom Terminology, Amazon Translate enables you to define how terms or names that are unique to certain organizations, domain, and industry get translated.

Language Identification

Amazon Translate is designed to identify a source language.

Batch and Real-Time Translations

Amazon Translate is designed to perform both batch translation and real-time translation.

Real-Time Document Translation

Amazon Translate is designed to support real-time document translation of various files.

Secure Machine Translation

Communication between your webpage or applications and the Amazon Translate service is designed to be protected.

Additional Information

For additional information about service controls, security features and functionalities, including, as applicable, information about storing, retrieving, modifying, restricting, and deleting data, please see https://docs.aws.amazon.com/index.html. This additional information does not form part of the Documentation for purposes of the AWS Customer Agreement available at http://aws.amazon.com/agreement, or other agreement between you and AWS governing your use of AWS’s services.