amazon-comprehend

Example of integrating & using Amazon Textract, Amazon Comprehend, Amazon Comprehend Medical, Amazon Kendra to automate the processing of documents for use cases such as enterprise search and discovery, control and compliance, and general business process workflow.

Open innovation with 60 minute cloud experiments on AWS

An inclusive chat that avoids negative messages and translates the content in the language that you choose, tracking the main topics of a chat room.

A boilerplate solution for processing image and PDF documents for regulated industries, with lineage and pipeline operations metadata services.

How to train a custom NLP classifier with AWS Comprehend?

QuickSeek is a chrome extension that allows you to easily search and navigate through a YouTube video, you can quickly find and watch only parts of the video that contain words you are looking for. The Chrome extension uses Amazon Transcribe to make the audio searchable and Amazon Comprehend to perform sentiment analysis on the transcript.

A web-app that aggregates a feed of positive news.

Automatically generate multi-language subtitles using AWS AI/ML services. Machine generated subtitles can be edited to improve accuracy and downstream tracks will automatically be regenerated based on the edits. Built on Media Insights Engine (https://github.com/awslabs/aws-media-insights-engine)

Get additional insights from your data by running it through Amazon Comprehend

Elasticsearch ingest processors using Amazon Comprehend for NLP analysis

This demo processes conversations in real-time with the Amazon Comprehend natural language processing (NLP) service to gain insights about what was said.

This repository contains a series of 4 jupyter notebooks demonstrating how AWS AI Services like Amazon Rekognition, Amazon Transcribe and Amazon Comprehend can help you extract valuable metadata from your video assets and store that information in a Graph database like Amazon Neptune for maximum query performance and flexibility.

A sample guide to building a serverless document processing application that can make intelligent flow-control decisions after classifying the input document type.

Use AWS Comprehend and GCP to do sentiment Analysis on Reviews for Comic series South Park and Rick&Morty.

Translate Slack message with flag emoji(e.g. 🇯🇵 🇺🇸 🇬🇧) reaction. 😄 Use only AWS Products(AWS Lambda functions in Go, Amazon Comprehend, Amazon Translate)

Sample audio transcription and analysis pipeline using Amazon Transcribe, Amazon Comprehend.

As an Intelligent Process Automation showcase. We combined Business Process Management with Artificial Intelligence, and the result was awesome! Find out more: https://www.novatec-gmbh.de/en/blog/ipa-camunda-comprehend/

Program to analyze tweet sentiment

Example php scripts making sigv4 signed aws api requests

Dataiku DSS plugin to use the Amazon Comprehend Medical API 🩺

Dataiku DSS plugin to use the Amazon Comprehend APIs 📚

In this module you will learn how to analyze topic modeling output from Amazon Comprehend, then perform topic modeling on two documents with a known topic structure.

Front-end website | Backend API | Authentication | Backend compute functions | Asynchronous reporting workflow | Distributed tracing | Monitoring features | Improving performance

Amazon Comprehend sample code that calls Sentiment and Key phrase APIs and does additional processing.

Provides a reliable political feed for readers to become knowledgeable and informed voters on the state political level.

This chapter covers the Amazon Rekognition service for analyzing the content of the images using various techniques. You will learn how to analyze faces and recognize celebrities in images. You will also be able to compare faces in different images to see how closely they match with each other.

Live Streamed Alexa Skill development to create a searchable index of the Alexa Office Hours Archives

This module teaches you how to design a chatbot using Amazon Lex by following the best design practices for conversational AI. You will start by learning the basics of chatbots. Then, you will use Amazon Lex to create a custom chatbot that gets the latest stock market quotes by recognizing the intent in text

In this module you will look at AWS AI services and examine an emerging computing paradigm – the Serverless Computing. We will then proceed to applying NLP and the Amazon Comprehend service to analyze documents.

A benchmark comparison project among the most popular sentiment analysis engines: VaderSentiment, TextBlob, Azure Text Analysis and Amazon Comprehend. The benchmarker is a python module that supports 3 datasets: IMDb, Sentiment140 and Twitter.