aws-samples / aws-samples/amazon-comprehend-examples
feature request - Layout Aware Custom Classification Example
- 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?
 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
Assessment
This issue has not been assessed yet.