aws-samples / aws-samples/amazon-comprehend-examples

feature request - Layout Aware Custom Classification Example

Open
#11 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
47
Forks
33
PR merge metrics
No merged PRs in 30d

Description

### Context
- https://aws.amazon.com/blogs/machine-learning/amazon-comprehend-document-classifier-adds-layout-support-for-higher-accuracy/

### Questions
- When using this method: https://boto3.amazonaws.com/v1/documentation/api/1.26.85/reference/services/comprehend/client/create_document_classifier.html

- Is "SEMI_STRUCTURED_DOCUMENT" equivalent to Native documents, maybe we can call that out, since the naming convention differs from the docs and the console?
![Screenshot 2023-11-27 at 1 04 44 PM](https://github.com/aws-samples/amazon-comprehend-examples/assets/11032490/3faf0caf-bf65-4631-ab80-46c67b14bfed) vs
https://docs.aws.amazon.com/comprehend/latest/dg/guidelines-and-limits.html

- I have an example showing the preparation work necessary to split up multi-page documents into the single page format, required for context awareness, but are there best practices published handling that "pre-work?"
- Also, are there published best practices to handle the 10,000 "Maximum number of pages across all documents" quota for semi-structured docs?

Thank you in advance.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.