Natural language holds a wealth of information like user sentiment and conversational intent. In this session, we'll demonstrate the capabilities of Amazon Comprehend, a natural language processing (NLP) service that uses machine learning to find insights and relationships in text. We'll show you how to build a VOC (Voice of the Customer) application and integrate it with other AWS services including AWS Lambda, Amazon S3, Amazon Athena, Amazon QuickSight, and Amazon Translate. We’ll also show you additional methods for NLP available through Amazon Sagemaker.
Level: 200-300
Speaker: Gopal Wunnava - Principal Solutions Architect, AWS
4. What are we going to do today?
Easily build a system that collects, translates, understands, and visualizes twitter
information based on your terms
Data
Catalog
Data Lake
• Capture Tweets in real-time
• Machine Translation
• Entity and KeyPhrase
• Sentiment Analysis
• Durably Save results
7. Amazon Kinesis – Real-Time Analytics
Easily collect, process, and analyze video and data streams in real time
Capture, process, and
store video streams
for analytics
Load data streams
into AWS data stores
Analyze data streams
with SQL
Build custom
applications that
analyze data streams
Kinesis Video Streams Kinesis Data Streams Kinesis Data Firehose Kinesis Data Analytics
9. Amazon Comprehend
A fully managed and continuously trained service that helps you extract insights
from unstructured text.
Sentiment Entities LanguagesKey phrases
Topic
modeling
11. Amazon Translate
A fully managed and continuously trained neural machine translation service that
translates text from one language to another
English <> Arabic, Simplified
Chinese, French, German,
Spanish and Portuguese
Language detection via
Amazon Comprehend
AWS Security Standards Available in US East (N,
Virginia), US East (Ohio),
US West (Oregon), and EU
(Ireland)
Easy to use and integrate via
CLI or SDKs
Best in class return on
investment
Translated text input
tagged inputs, e.g. HTML
Real-time translation of
~30 words, i.e. <500ms
12. Easy to Use & Integrate
• Use through Command Line Tools or AWS SDKs
• Integrate into your application or call externally
• Python example:
import boto3
Amazon.translate = boto3.client(service_name=‘translate')
result = Amazon.translate(Text="Hello, World",
SourceLanguageCode="en", TargetLanguageCode="de")
print('TranslatedText: ' + result.get('TranslatedText'))
13. Querying our Data Lake
Amazon
S3
<bucket>/raw
<bucket>/enriched
AWS Glue Data
Catalog
Describes
Amazon
Athena
SQL
Uses
Queries
17. Resources
The AWS CloudFormation template will create all the ingestion components shown
in this session, except for the Amazon S3 notification for AWS Lambda (depicted as
the dotted blue line). In the AWS Management Console, launch the CloudFormation
Template. Refer to the blog more details: https://aws.amazon.com/blogs/machine-
learning/build-a-social-media-dashboard-using-machine-learning-and-bi-services/
Webinar: https://www.youtube.com/watch?v=wwOQvjogc7Q
Additional questions about the demo? Reach to snivelyb@amazon.com