aws-samples / aws-samples/amazon-textract-code-samples

Issue with Generating Key-Value Pairs from CMS 1500 Form

Open
#59 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
449
Forks
262
PR merge metrics
No merged PRs in 30d

Description

Hi,
I am working on reading the form and processing data from CMS 1500 using the provided code. However, I have noticed several issues with the key-value pair generation. The current implementation fails to fetch many details from the form accurately and incorrectly processes some elements. [REPO LINK ](https://github.com/aws-samples/amazon-textract-code-samples/blob/3fb9e1cd3c0a8035aa623f0efe79a16a310f758a/python/extraction-parsers/cms1500-parser.ipynb)
Problems Encountered:
- Many key-value pairs are not being extracted correctly.
- Some values are not being associated correctly with their keys.
- The code seems unable to handle certain sections of the form, such as tables.

![image](https://github.com/user-attachments/assets/09cad0fa-c83e-4f0c-9a8d-dceeea0818de)
In your test sample form I am not seeing any of the details belongs to the table
Please do respond asap :(

Contributor guide

Open the contributing guide

Research direction

Open extraction-parsers/cms1500-parser.ipynb and run it against the referenced CMS 1500 test sample. Inspect the generated key-value pairs, especially the table section, and compare them with the form image; the issue is complete when the missing details and key associations are extracted accurately.

Written by the indexing model from the issue text.

Assessment

Tech stack
aws, jupyter-notebook, python
Domain
ai, cloud, data
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.