You're reading from Natural Language Processing with AWS AI Services Derive strategic insights from unstructured data with Amazon Textract and Amazon Comprehend

Product type Paperback

Published in Nov 2021

Publisher Packt

ISBN-13 9781801812535

Length 508 pages

Edition 1st Edition

Languages

Processing

Tools

Amazon Textract

Concepts

Mobile Application Development

Authors (2):

Mona M

Premkumar Rangarajan

View More author details

Table of Contents (23) Chapters

Preface

1. Section 1:Introduction to AWS AI NLP Services

2. Chapter 1: NLP in the Business Context and Introduction to AWS AI Services FREE CHAPTER

3. Chapter 2: Introducing Amazon Textract

4. Chapter 3: Introducing Amazon Comprehend

5. Section 2: Using NLP to Accelerate Business Outcomes

6. Chapter 4: Automating Document Processing Workflows

7. Chapter 5: Creating NLP Search

8. Chapter 6: Using NLP to Improve Customer Service Efficiency

9. Chapter 7: Understanding the Voice of Your Customer Analytics

10. Chapter 8: Leveraging NLP to Monetize Your Media Content

11. Chapter 9: Extracting Metadata from Financial Documents

12. Chapter 10: Reducing Localization Costs with Machine Translation

13. Chapter 11: Using Chatbots for Querying Documents

14. Chapter 12: AI and NLP in Healthcare

15. Section 3: Improving NLP Models in Production

16. Chapter 13: Improving the Accuracy of Document Processing Workflows

17. Chapter 14: Auditing Named Entity Recognition Workflows

18. Chapter 15: Classifying Documents and Setting up Human in the Loop for Active Learning

19. Chapter 16: Improving the Accuracy of PDF Batch Processing

20. Chapter 17: Visualizing Insights from Handwritten Content

21. Chapter 18: Building Secure, Reliable, and Efficient NLP Solutions

22. Other Books You May Enjoy

Adding human reviews to your document processing pipelines

We covered how A2I works in general with any AWS AI service using an architecture. In this section, we will talk specifically about how Amazon A2I integrates with Amazon Textract so that you can automate your existing document workflows with a HITL. We will also show you a walkthrough on how to set up a human review workflow using the AWS Console.

Let's start by walking through how Amazon A2I works with Amazon Textract:

Figure 13.2 – Amazon A2I with Amazon Textract

Your scanned documents are sent to Amazon Textract. Amazon Textract extracts text, key-value pairs, and tables from the document. Now for this extracted text, key-value pairs, and tables, you also get confidence scores. You can set up a threshold that Amazon A2I triggers to create human review loops. You can set up a threshold with Amazon Textract for three things:

For any missing keys in case of key-value pair detection...

The rest of the chapter is locked

You're reading from Natural Language Processing with AWS AI Services Derive strategic insights from unstructured data with Amazon Textract and Amazon Comprehend

Table of Contents (23) Chapters

Adding human reviews to your document processing pipelines

Unlock this book and the full library FREE for 7 days

Authors (2)