TEXTRACT: Anayze Table of Contents

Using Textract for a table of contents where each line has** TITLE . . . . Author PageNo.** Resultant table has Title and Author merges ignoring dot-leader as one column and page numbers has 2nd column. How can I get Textract to treat dot-leader as a column separator

Topics

Machine Learning & AI

Tags

Amazon Textract

Language

English

Alan Greenberg

asked 6 months ago229 views

2 Answers

Newest
Most votes
Most comments

Are these answers helpful? Upvote the correct answer to help the community benefit from your knowledge.

Could you provide sample image for better understanding?

hyuno-aws

answered 6 months ago

Would it be feasible to process text before textract ? So you could insert some kind of well known separator to be easily recognized by the ML behind it.

EXPERT

Giovanni Lauria

answered 6 months ago

Relevant content

Textract Table Odd Behavior on 1 out of 5 pages
rePost-User-0694546
asked 2 years ago
Textract: pretrained tables?
Accepted Answer
jminvoke
asked 3 months ago
Textract - Not Reading All Columns of a table
rePost-User-9273407
asked 2 years ago
Has anyone extracted multi-page pdf tables using the Textract Javascript v3 sdk?
Zaahid
asked a month ago
How do I manage and optimize Iceberg tables for efficient data storage and querying?
AWS OFFICIALUpdated 2 months ago
How do I streamline the creation of a global secondary index for a DynamoDB table?
AWS OFFICIALUpdated a month ago
How do I resolve the error "Cannot create a replica of table in region" when I try to add a replica to my DynamoDB Global Table?
AWS OFFICIALUpdated 4 months ago
How do I manage the number of table versions in AWS Glue for Apache Iceberg tables?
AWS OFFICIALUpdated a month ago
Monitoring and troubleshooting query performance using system tables on Amazon Redshift provisioned clusters
SUPPORT ENGINEER
Srinivas Naidu
published a month ago
Migrating Glue Data Catalog tables to use Apache Iceberg open table format using Athena
EXPERT
Hamzah Chaudhry
published 5 months ago