Amazon Comprehend now supports Amazon Sagemaker GroundTruth training datasets for custom model training
You can now train Custom Named Entity Recognition and Custom Classification models in Amazon Comprehend using training datasets from Amazon Sagemaker GroundTruth. You can use Comprehend’s Custom Named Entity Recognition to identify terms that are specific to your industry or organization. For example, you can instantly extract product names, financial entities or any term relevant to you from text data. Similarly, you can use Comprehend’s Custom Classification to assign categories relevant to your use case to text data.
Source:: Amazon AWS