cocacola-lab/ChatIE
Zero-shot information extraction system using ChatGPT via multi-turn question-answering for entity, relation, and event extraction.
Not currently ranked — collecting fresh signals.
star history
ChatIE is a two-stage framework that transforms zero-shot information extraction into a multi-turn question-answering problem, leveraging ChatGPT for entity-relation triple extraction, named entity recognition, and event extraction. The approach achieves competitive performance on six datasets across two languages without requiring annotated training data. It provides a tool-based implementation enabling local execution with OpenAI API keys.
Frequently asked
- What is cocacola-lab/ChatIE?
- Zero-shot information extraction system using ChatGPT via multi-turn question-answering for entity, relation, and event extraction.
- Is ChatIE open source?
- Yes — cocacola-lab/ChatIE is an open-source project tracked on heatdrop.
- What language is ChatIE written in?
- cocacola-lab/ChatIE is primarily written in Python.
- How popular is ChatIE?
- cocacola-lab/ChatIE has 826 stars on GitHub.
- Where can I find ChatIE?
- cocacola-lab/ChatIE is on GitHub at https://github.com/cocacola-lab/ChatIE.