KomeijiForce/CoTAM

Official Implementation of the ACL2024 Findings paper "Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation"

19
/ 100
Experimental

This tool helps AI/ML developers quickly create more training examples for text classification models, especially when you only have a small amount of initial data. It takes your existing text data and an OpenAI API key, then uses a large language model to generate diverse, high-quality synthetic training examples. The output is an expanded dataset that you can use to fine-tune smaller language models, making them more accurate for tasks like sentiment analysis, topic categorization, or intent recognition.

No commits in the last 6 months.

Use this if you are developing or fine-tuning smaller language models for text classification and need to boost their performance, but have limited real-world training data.

Not ideal if you are looking for a no-code solution, do not have an OpenAI API key, or your primary task is not text classification.

NLP-development text-classification data-augmentation LLM-fine-tuning machine-learning-engineering
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

18

Forks

1

Language

Python

License

Last pushed

May 18, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/KomeijiForce/CoTAM"

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