Book Image

Natural Language Processing with AWS AI Services

By : Mona M, Premkumar Rangarajan
Book Image

Natural Language Processing with AWS AI Services

By: Mona M, Premkumar Rangarajan

Overview of this book

Natural language processing (NLP) uses machine learning to extract information from unstructured data. This book will help you to move quickly from business questions to high-performance models in production. To start with, you'll understand the importance of NLP in today’s business applications and learn the features of Amazon Comprehend and Amazon Textract to build NLP models using Python and Jupyter Notebooks. The book then shows you how to integrate AI in applications for accelerating business outcomes with just a few lines of code. Throughout the book, you'll cover use cases such as smart text search, setting up compliance and controls when processing confidential documents, real-time text analytics, and much more to understand various NLP scenarios. You'll deploy and monitor scalable NLP models in production for real-time and batch requirements. As you advance, you'll explore strategies for including humans in the loop for different purposes in a document processing workflow. Moreover, you'll learn best practices for auto-scaling your NLP inference for enterprise traffic. Whether you're new to ML or an experienced practitioner, by the end of this NLP book, you'll have the confidence to use AWS AI services to build powerful NLP applications.
Table of Contents (23 chapters)
1
Section 1:Introduction to AWS AI NLP Services
5
Section 2: Using NLP to Accelerate Business Outcomes
15
Section 3: Improving NLP Models in Production

Summary

In this chapter, we covered two things using a reference architecture as well as a code walkthrough. Firstly, we covered how you can extract data from various types of documents, such as pay stubs, bank statements, or identification cards using Amazon Textract. Then, we learned how you can perform some post-processing to create a labeled training file for Amazon Comprehend custom classification training.

We showed you that even with 36 bank statement documents and 24 pay stubs as a training sample, you can achieve really good accuracy using Amazon Comprehend transfer-learning capabilities and AutoML with document or text classification. Obviously, the accuracy improves with more data.

Then, you learned how to set up a training job in the AWS Management Console and how to set up a real-time classification endpoint using the AWS Management Console.

Secondly, you learned how you can set up humans in the loop with the real-time classification endpoint to review/verify...