/amazon-comprehend-examples

Primary LanguageJupyter NotebookMIT No AttributionMIT-0

Amazon Comprehend Examples

This repository contains scripts, tutorials, and data for our customers to use when experimenting with features released by AWS Comprehend.

Packages

  1. comprehend_groundtruth_integration: This package contains shell scripts for conversion of SageMaker GroundTruth NER and MultiClass/MultiLabel labeling job output to formats suitable for use with Comprehend's Custom NER and Custom Document Classifier APIs.

  2. amazon_comprehend_events_tutorial: This package contains a Jupyter notebook, supporting script, and sample data necessary to produce tabulations and visualizations of Comprehend Events asynchronous API output.

Amazon Comprehend Solutions and Resources

Amazon Comprehend Document Search- Using Amazon Comprehend, Amazon Elasticsearch with Kibana, Amazon S3, Amazon Cognito to search over large number of documents such as pdf files.https://github.com/aws-samples/amazon-comprehend-doc-search

Amazon Textract Comprehend Image Search with Elasticsearch https://github.com/aws-samples/amazon-textract-comprehend-OCRimage-search-and-analyze

Easily setup human review of your NLP based Entity Recognition workflows with Amazon SageMaker Ground Truth, Amazon Comprehend AutoML and Amazon Augmented AI (A2I) - https://github.com/aws-samples/augmentedai-comprehendner-groundtruth

Deriving conversational insights from invoices with Amazon Textract, Amazon Comprehend, and Amazon Lex - https://github.com/aws-samples/aws-textract-comprehend-lex-chatbot

Active learning workflow for Amazon Comprehend Custom Classification models with Amazon Augmented AI https://github.com/aws-samples/amazon-comprehend-active-learning-framework

Easily setup built-in human review loops for NLP based entity recognition workflows using Amazon SageMaker Ground Truth, Amazon Comprehend and Amazon Augmented AI https://github.com/aws-samples/augmentedai-comprehendner-groundtruth

Amazon Transcribe Comprehend Podcast- A demo application that transcribes and indexes podcast episodes so the listeners can explore and discover episodes of interest and podcast owners can do analytics on the content over time. This solution leverages Amazon Transcribe, Amazon Comprehend, Amazon Elasticsearch, AWS Step Functions and AWS Lambda.https://github.com/aws-samples/amazon-transcribe-comprehend-podcast

Notebooks and recipes for creating custom entity recognizer for Amazon comprehend https://github.com/aws-samples/amazon-comprehend-custom-entity Document Analysis Solution using Amazon Textract, Amazon Comprehend and Amazon A2I https://github.com/aws-samples/amazon-textract-comprehend-a2i nlp-analysis-demo - The purpose of this demo is to build a stack that uses Amazon Comprehend and Amazon Textract to analyze unstructured data and generate insights and trends https://github.com/aws-samples/nlp-textract-comprehend-demo

Workshops

workshop-textract-comprehend-es https://github.com/aws-samples/workshop-textract-comprehend-es

LICENSE

This library is licensed under the MIT-0 License. See the LICENSE file.