j6mes/acl2021-factual-error-correction

ACL 2021

39
/ 100
Emerging

This project helps fact-checkers and content reviewers identify and correct factual errors in text by providing tools to pinpoint the exact parts of a statement that are incorrect and then suggest corrections. It takes a claim (e.g., a news headline or social media post) and supporting evidence (e.g., from a knowledge base or search results) as input. The output is a revised claim with the factual errors corrected, making it useful for journalists, researchers, or anyone focused on content veracity.

No commits in the last 6 months.

Use this if you need to automatically or semi-automatically find and fix factual inaccuracies in written content based on provided evidence.

Not ideal if you need a tool for grammar checking or stylistic improvements rather than factual accuracy, or if you don't have access to supporting evidence for verification.

fact-checking content-verification text-correction information-accuracy content-moderation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

27

Forks

7

Language

Python

License

Apache-2.0

Last pushed

May 24, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/j6mes/acl2021-factual-error-correction"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.