yumeng5/WeSTClass

[CIKM 2018] Weakly-Supervised Neural Text Classification

45
/ 100
Emerging

This project helps classify large collections of text documents into categories, even when you only have a few examples or descriptions for each category. You provide either class names, a few keywords per class, or a small set of pre-labeled documents. The system then outputs predicted category labels for all your unclassified documents. This is useful for researchers, data scientists, or analysts who need to organize vast amounts of text data with minimal manual labeling.

No commits in the last 6 months.

Use this if you need to automatically categorize a large corpus of text documents but have very limited manually labeled examples.

Not ideal if you have a substantial amount of manually labeled data available for training, as this tool is specifically designed for weak supervision scenarios.

text-classification document-organization information-extraction content-categorization data-labeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

78

Forks

29

Language

Python

License

Apache-2.0

Last pushed

Dec 06, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/yumeng5/WeSTClass"

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