p-karisani/self_pretraining

A classification model

33
/ 100
Emerging

This project helps classify text documents into two categories (e.g., positive/negative sentiment, spam/not-spam) even when you have very few labeled examples but many unlabeled ones. You provide a list of documents, some with categories and many without, and it outputs a highly accurate classification model ready to categorize new documents. It's designed for data scientists or researchers who need to categorize large volumes of text efficiently.

No commits in the last 6 months.

Use this if you need to classify text but have limited labeled data and a large pool of unlabeled text that could help train a better model.

Not ideal if you have abundant labeled data for your text classification task or if your documents require multi-label or multi-class classification beyond a simple binary choice.

text-classification sentiment-analysis document-categorization natural-language-processing semi-supervised-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

21

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Apr 24, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/p-karisani/self_pretraining"

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