Explain the features of Amazon Comprehend

In this recipe, we will learn about Amazon Comprehend. We will also learn about the features of Amazon Comprehend.

Recipe Objective - Explain the features of Amazon Comprehend?

The Amazon Comprehend is widely used and is defined as a natural language processing (NLP) service which uses machine learning to find insights and relationships in text and no further machine learning experience is required. Amazon Comprehend uses machine learning to help users uncover the insights and relationships in their unstructured data. Amazon Comprehend service identifies the language of the text, extracts the key phrases, places, people, brands, or events, understands how positive or negative text is, analyzes the text using the tokenization and parts of speech and automatically organizes a collection of text files by the topic. Users can also use the AutoML capabilities in Amazon Comprehend to build the custom set of entities or text classification models which are tailored uniquely to the organization’s needs. Amazon Comprehend console and data access roles can be requested through submission of two AMS Service RFCs: Request access to the Amazon Comprehend by submitting an RFC with the Management, AWS service, Self-provisioned service, Add (ct-3qe6io8t6jtny) change type and this RFC provisions the following IAM role to user's account, customer_comprehend_console_role. And After it's provisioned in the user's account, users must onboard the role in their federation solution. Amazon Comprehend provides a service to create New IAM Role functionality through the Amazon Comprehend console.

Build Log Analytics Application with Spark Streaming and Kafka

Benefits of Amazon Comprehend

  • The Amazon Comprehend uncovers the valuable insights from text in documents, customer support tickets, product reviews, emails, social media feeds, and more and thus provides a machine learning service to find insights. Amazon Comprehend simplifies the document processing workflows by extracting text, key phrases, topics, sentiment, and more from documents such as insurance claims. Amazon Comprehend enables differentiating users' business by training the model to classify documents and identify terms, with no machine learning experience required. Amazon Comprehend protects and controls who has access to sensitive data by identifying and redacting personally Identifiable Information (PII) from the documents.

System Requirements

  • Any Operating System(Mac, Windows, Linux)

This recipe explains Amazon Comprehend and Features of Amazon Comprehend.

Features of Amazon Comprehend

    • It provides Custom Entity Recognition

Amazon Comprehend provides Custom entity recognition which allows users to customize Amazon Comprehend to identify terms that are specific to the domain. Further using AutoML, Amazon Comprehend will learn from a small set of examples (for example, the list of policy numbers, claim numbers, or SSN), and then train the private, custom model to recognize these terms such as the claim numbers in any other block of text within PDFs, plain text, or Microsoft Word documents – i.e. no machine learning required.

    • It provides Custom Classification

Amazon Comprehend provides the Custom Classification API which enables users to easily build custom text classification models using the business-specific labels without learning Machine Learning. For eg, a User's customer support organization can use Custom Classification to further automatically categorize inbound requests by problem type based on how the customer has described the issue. With the user's custom model, it is further easy to moderate website comments, triage customer feedback, and organize workgroup documents.

    • It provides Entity Recognition

Amazon Comprehend provides Entity Recognition API which returns the named entities ("People," "Places," "Locations," etc.) which are automatically categorized based on the provided text.

    • It provides Sentiment Analysis

Amazon Comprehend provides Sentiment Analysis API which returns the overall sentiment of a text (Positive, Negative, Neutral, or Mixed).

    • It provides PII Identification and Redaction

Amazon Comprehend ML capabilities to detect and redact personally identifiable information (PII) in the customer emails, support tickets, product reviews, social media, and more and No Machine Learning experience is required. For eg, users can analyze support tickets and knowledge articles to detect the PII entities and redact text before users index the documents in the search solution. Further, after that, search solutions are free of the PII entities in documents.

    • It provides Keyphrase Extraction

Amazon Comprehend provides the Keyphrase Extraction API which returns the key phrases or talking points and a confidence score to support that this is the key phrase.

    • It provides Events Detection

Amazon Comprehend provides comprehend Events that lets users extract the event structure from the document, distilling pages of text down to easily processed data for consumption by the Artificial Intelligence applications or graph visualization tools. This API allows users to answer who-what-when-where questions over large document sets, at scale and without prior NLP experience. So, Amazon Comprehend Events can be used to extract granular details about real-world events and associated entities expressed in the unstructured text.

What Users are saying..

profile image

Ameeruddin Mohammed

ETL (Abintio) developer at IBM
linkedin profile url

I come from a background in Marketing and Analytics and when I developed an interest in Machine Learning algorithms, I did multiple in-class courses from reputed institutions though I got good... Read More

Relevant Projects

How to deal with slowly changing dimensions using snowflake?
Implement Slowly Changing Dimensions using Snowflake Method - Build Type 1 and Type 2 SCD in Snowflake using the Stream and Task Functionalities

AWS Project for Batch Processing with PySpark on AWS EMR
In this AWS Project, you will learn how to perform batch processing on Wikipedia data with PySpark on AWS EMR.

Retail Analytics Project Example using Sqoop, HDFS, and Hive
This Project gives a detailed explanation of How Data Analytics can be used in the Retail Industry, using technologies like Sqoop, HDFS, and Hive.

EMR Serverless Example to Build a Search Engine for COVID19
In this AWS Project, create a search engine using the BM25 TF-IDF Algorithm that uses EMR Serverless for ad-hoc processing of a large amount of unstructured textual data.

Snowflake Real Time Data Warehouse Project for Beginners-1
In this Snowflake Data Warehousing Project, you will learn to implement the Snowflake architecture and build a data warehouse in the cloud to deliver business value.

Spark Project-Analysis and Visualization on Yelp Dataset
The goal of this Spark project is to analyze business reviews from Yelp dataset and ingest the final output of data processing in Elastic Search.Also, use the visualisation tool in the ELK stack to visualize various kinds of ad-hoc reports from the data.

Build an ETL Pipeline on EMR using AWS CDK and Power BI
In this ETL Project, you will learn build an ETL Pipeline on Amazon EMR with AWS CDK and Apache Hive. You'll deploy the pipeline using S3, Cloud9, and EMR, and then use Power BI to create dynamic visualizations of your transformed data.

Project-Driven Approach to PySpark Partitioning Best Practices
In this Big Data Project, you will learn to implement PySpark Partitioning Best Practices.

Web Server Log Processing using Hadoop in Azure
In this big data project, you will use Hadoop, Flume, Spark and Hive to process the Web Server logs dataset to glean more insights on the log data.

Learn Real-Time Data Ingestion with Azure Purview
In this Microsoft Azure project, you will learn data ingestion and preparation for Azure Purview.