timoschick/pet

This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"

50
/ 100
Established

This tool helps you classify text and understand language relationships, even when you have very little data. You provide text examples and the tool outputs categories or relationships, like whether a review is positive or negative. It's designed for anyone who needs to make sense of text data quickly, such as researchers analyzing surveys, marketers categorizing customer feedback, or HR managers screening resumes.

1,627 stars. No commits in the last 6 months.

Use this if you need to classify or analyze text with high accuracy but have very few labeled examples, or even no examples at all.

Not ideal if you have a large, well-labeled dataset for your text classification needs, as traditional supervised methods might be simpler to implement.

text-classification natural-language-inference low-resource-nlp data-labeling text-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

1,627

Forks

282

Language

Python

License

Apache-2.0

Last pushed

Jun 12, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/timoschick/pet"

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