Yinghao-Li/GnO-IE
Code for "A Simple but Effective Approach to Improve Structured Language Model Output for Information Extraction"
This project helps researchers and data scientists extract specific pieces of information from unstructured text, like identifying diseases in medical reports or relationships between entities in scientific papers. It takes raw text as input and outputs structured data, such as lists of named entities or identified relationships, which can then be used for further analysis or database population. This tool is ideal for those working with large volumes of domain-specific text who need to automate data extraction tasks.
No commits in the last 6 months.
Use this if you need to reliably extract specific facts or relationships from text documents using large language models, especially when precision and accuracy of structured output are critical.
Not ideal if you're looking for a simple, out-of-the-box application for general text summarization or generation, or if you don't have access to large language models like GPT or Llama.
Stars
15
Forks
2
Language
—
License
Apache-2.0
Category
Last pushed
Mar 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Yinghao-Li/GnO-IE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
williamliujl/CMExam
A Chinese National Medical Licensing Examination dataset and large languge model benchmarks
zjunlp/IEPile
[ACL 2024] IEPile: A Large-Scale Information Extraction Corpus
StefanHeng/ProgGen
Code for paper "ProgGen: Generating Named Entity Recognition Datasets Step-by-step with...
MaheshJakkala/naamapadam-multilingual-ner
Benchmarking NER on Naamapadam across 7 Indic languages. EDA + model training for...
yaoyiran/BLI-Reading-List
A 2024 Reading List for Bilingual Lexicon Induction (BLI) / Word Translation. Frequently Updated.