j6mes/acl2021-factual-error-correction
ACL 2021
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.
Stars
27
Forks
7
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
n-waves/multifit
The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model...
princeton-nlp/SimCSE
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
yxuansu/SimCTG
[NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation
alibaba-edu/simple-effective-text-matching
Source code of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".
Shark-NLP/OpenICL
OpenICL is an open-source framework to facilitate research, development, and prototyping of...