HeyyyyyyG/CFIE

PyTorch implementation for our proposed CFIE in EMNLP 2021 paper "Uncovering Main Causalities for Long-tailed Information Extraction".

30
/ 100
Emerging

This project helps data scientists and NLP practitioners extract structured information from complex, unstructured text documents. It takes raw text data as input and produces categorized entities and events, even when faced with imbalanced datasets where some categories are very rare. The key benefit is more accurate extraction by identifying direct causal relationships, reducing errors from spurious correlations.

No commits in the last 6 months.

Use this if you need to perform information extraction (like named entity recognition or event detection) on text data, especially when dealing with imbalanced datasets where common entities might overshadow rarer, but important, ones.

Not ideal if your primary goal is simple keyword extraction or if your datasets are perfectly balanced and do not suffer from long-tailed distributions.

Information Extraction Natural Language Processing Text Analytics Data Annotation Entity Recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

26

Forks

2

Language

Python

License

GPL-3.0

Last pushed

Jan 05, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/HeyyyyyyG/CFIE"

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