FreedomIntelligence/Evaluation-of-ChatGPT-on-Information-Extraction

An Evaluation of ChatGPT on Information Extraction task, including Named Entity Recognition (NER), Relation Extraction (RE), Event Extraction (EE) and Aspect-based Sentiment Analysis (ABSA).

29
/ 100
Experimental

This project helps researchers and developers understand the capabilities and limitations of large language models like ChatGPT for information extraction tasks. It takes raw text or pre-processed datasets and outputs detailed performance metrics, error analyses, and robustness insights across various extraction types. The primary users are researchers in natural language processing or AI developers evaluating LLMs for production applications.

134 stars. No commits in the last 6 months.

Use this if you are a researcher or developer who needs to thoroughly evaluate how well ChatGPT performs on tasks like identifying entities, relationships, events, or sentiment from text.

Not ideal if you are looking for a pre-built solution to directly perform information extraction on your own data without extensive setup or analysis.

natural-language-processing large-language-models information-extraction AI-evaluation text-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

134

Forks

11

Language

Python

License

Last pushed

Jan 17, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/FreedomIntelligence/Evaluation-of-ChatGPT-on-Information-Extraction"

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