ritaranx/NeST

[AAAI 2023] This is the code for our paper `Neighborhood-Regularized Self-Training for Learning with Few Labels'.

27
/ 100
Experimental

This project helps data scientists, machine learning engineers, and researchers classify text documents efficiently when labeled data is scarce. You provide a small set of labeled text documents and a larger pool of unlabeled documents, and it outputs a model capable of accurately categorizing new, unseen text. This is ideal for anyone working on text classification tasks across various domains.

No commits in the last 6 months.

Use this if you need to classify documents into categories but have very few examples for each category and a lot of unclassified text.

Not ideal if you have a large, well-labeled dataset already, as this method is specifically designed for low-resource scenarios.

sentiment-analysis news-topic-classification chemical-relation-extraction document-categorization text-analytics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

MIT

Last pushed

Jan 11, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/ritaranx/NeST"

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