KomeijiForce/MetaIE
This is a meta-model distilled from LLMs for information extraction. This is an intermediate checkpoint that can be well-transferred to all kinds of downstream information extraction tasks.
This project helps machine learning engineers and researchers to quickly extract specific pieces of information from large volumes of text. You input a collection of text documents (your corpus) and, after fine-tuning, the system outputs structured data extracted from that text, such as names, dates, or product codes. This is designed for practitioners who build and deploy natural language processing models.
No commits in the last 6 months.
Use this if you are developing custom information extraction models and want a strong base model that can be adapted efficiently to various tasks and languages with less training data.
Not ideal if you are an end-user looking for a ready-to-use information extraction tool without any model development or fine-tuning.
Stars
28
Forks
2
Language
Python
License
—
Category
Last pushed
Feb 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/KomeijiForce/MetaIE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zjunlp/OpenUE
[EMNLP 2020] OpenUE: An Open Toolkit of Universal Extraction from Text
OpenSextant/Xponents
Geographic Place, Date/time, and Pattern entity extraction toolkit along with text extraction...
BaptisteBlouin/EventExtractionPapers
A list of NLP resources focused on event extraction task
philipperemy/stanford-openie-python
Stanford Open Information Extraction made simple!
uma-pi1/minie
An open information extraction system that provides compact extractions