rz-zhang/PRBoost

The codes for our ACL'22 paper: PRBOOST: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning.

15
/ 100
Experimental

PRBoost helps machine learning practitioners efficiently categorize unstructured text data by identifying patterns in labeled examples. You provide a small set of labeled text, and it generates rules to classify similar texts. This is ideal for data scientists or NLP engineers who need to quickly label large datasets without extensive manual annotation.

No commits in the last 6 months.

Use this if you have a limited amount of labeled text data and need to rapidly create rules for classifying a much larger unlabeled text corpus.

Not ideal if you require explainable rules based on human-interpretable linguistic patterns, as the rules are automatically discovered prompts.

text-classification natural-language-processing weak-supervision data-labeling machine-learning-engineering
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

35

Forks

Language

License

Last pushed

Mar 18, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/rz-zhang/PRBoost"

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