# timoschick/pet

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/timoschick-pet).**

0 stars · 0 forks

## Links

- GitHub: https://github.com/timoschick/pet
- awesome-repositories: https://awesome-repositories.com/repository/timoschick-pet.md

## Description

This repository contains the code for Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference and It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners. The papers introduce pattern-exploiting training (PET), a semi-supervised…

## Tags

### Part of an Awesome List

- [Prompt Tuning Techniques](https://awesome-repositories.com/f/awesome-lists/ai/prompt-tuning-techniques.md) — Pattern-exploiting training for few-shot text classification.
- [Semantic Text Matching](https://awesome-repositories.com/f/awesome-lists/ai/semantic-text-matching.md) — Few-shot text classification using cloze-style pattern exploitation.