YujiaBao/Distributional-Signatures

"Few-shot Text Classification with Distributional Signatures" ICLR 2020

48
/ 100
Emerging

This project helps classify short texts into categories, even when you only have a few examples for each category. It takes in various text types like news articles, product reviews, or headlines, and outputs the correct category for new, unseen texts. It's ideal for data scientists, researchers, or anyone building AI models who need to categorize text efficiently with minimal labeled data.

261 stars. No commits in the last 6 months.

Use this if you need to quickly classify text into categories but have very few labeled examples available for each category.

Not ideal if you have a large amount of labeled data for all your text categories, as traditional supervised learning methods might be more straightforward.

text-classification natural-language-processing content-categorization data-labeling AI-model-training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

261

Forks

54

Language

Python

License

MIT

Last pushed

Dec 17, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/YujiaBao/Distributional-Signatures"

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