Amazon Lex
Amazon Lex is a service for building conversational interfaces into any application using voice and text. Amazon Lex provides the advanced deep learning functionalities of automatic speech recognition (ASR) for converting speech to text, and natural language understanding (NLU) to recognize the intent of the text, to enable you to build applications with highly engaging user experiences and lifelike conversational interactions.
Amazon Translate
Amazon Translate is a neural machine translation service that delivers fast, high-quality, and affordable language translation.
![]() Real-time Translation |
![]() Neural Language Processing |
---|---|
![]() 12+ Language Pairs |
![]() Automatic Language Detection |
Amazon Comprehend
Amazon Comprehend is a natural language processing (NLP) service that uses machine learning to find insights and relationships in text. Amazon Comprehend identifies the language of the text; extracts key phrases, places, people, brands, or events; understands how positive or negative the text is; and automatically organizes a collection of text files by topic.
Demo 1: Amazon Connect & Lex Integration
Give us a call! With the Amazon Connect call center using lex integration, you can trigger lambda functions using only your voice to vote in real time. This demo was built by Randall Hunt, AWS Solutions Architect.
Learn more about how Amazon Connect can make setting up your next call center easier, cheaper, and faster here: Amazon Connect
Demo 2: Amazon Comprehend & Translate Integration
Leave a comment on a vehicle and see how Comprehend automatically detects sentiment and labels comments. You can also use Translate to change the language of the comment. These two services combined allow you to create a dynamic messageboard that will inform you on user sentiment, even if the comments are in different languages! Pretty Cool :) This demo was built by Giuseppe Porcelli and Diego Natali, AWS Solutions Architects.
Link to Architecture Diagram here
Demo 3: Social Media Analytics
The Social Media Analytics solution utilizes Amazon Translate, Amazon Comprehend, Amazon Kinesis, Amazon Athena, and Amazon QuickSight to build a natural-language-processing (NLP)-powered social media dashboard for tweets during the PyeongChang 2018 Olympics. The architecture uses a serverless data processing and machine learning (ML) pipeline to provide multi-lingual social media dashboard of tweets within Amazon QuickSight. By leveraging API-driven ML services, developers can easily add intelligence to any application, such as computer vision, speech, language analysis, and chatbot functionality by simply calling a highly available, scalable, and secure endpoint. These building blocks, coupled with very little code, use the AWS platform to perform language translation and natural language processing on the tweets flowing through the system.
Quicksight Login:
Account Name: wwps-aiml-demoportal
Username: demo
Password: AIMLDemo123
Link to Architecture Diagram here
Demo 4: Lex OrderFlowers Chatbot Web App
Lex OrderFlowers Chatbot Full Size
This is a sample Amazon Lex web interface. It provides a chatbot UI component that can be integrated in your website. The interface allows to interact with a Lex bot directly from a browser using text or voice. The chatbot UI can be displayed either as a full page or embedded in an iframe. This demo uses the OrderFlowers Lex Blueprint
Learn more about the Lex Web UI here: AWSLabs Repository
Learn more about the OrderFlowers Blueprint here: Create a Bot
Demo 5: Comprehend & Transcribe for Video Analytics
Using Amazon Transcribe's speech to text capabilities, you can transcribe a video with timestamps and puncutation. This information can then be pass on to Amazon Comprehend for entity extraction, key phrase analysis, and other metrics.