bigai-nlco/DocGNRE
[EMNLP 2023] Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models
This tool helps researchers and data scientists working with unstructured text documents to automatically identify and extract relationships between entities. It takes in large collections of documents and generates an enhanced dataset of 'triples' (subject-relation-object) using Large Language Models and Natural Language Inference, which can then be used to train and evaluate relation extraction models.
No commits in the last 6 months.
Use this if you need to rapidly create or expand high-quality, labeled datasets for document-level relation extraction without extensive manual annotation.
Not ideal if you require 100% human-verified accuracy for every relation, as it relies on automated, 'distantly supervised' methods.
Stars
17
Forks
2
Language
Python
License
MIT
Category
Last pushed
Oct 30, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/bigai-nlco/DocGNRE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zjukg/KG-LLM-Papers
[Paper List] Papers integrating knowledge graphs (KGs) and large language models (LLMs)
nancheng58/Awesome-LLM4RS-Papers
Large Language Model-enhanced Recommender System Papers
HKUDS/UrbanGPT
[KDD'2024] "UrbanGPT: Spatio-Temporal Large Language Models"
HKUDS/GraphGPT
[SIGIR'2024] "GraphGPT: Graph Instruction Tuning for Large Language Models"
HKUDS/HiGPT
[KDD'2024] "HiGPT: Heterogenous Graph Language Models"