PrithivirajDamodaran/Alt-ZSC

Alternate Implementation for Zero Shot Text Classification: Instead of reframing NLI/XNLI, this reframes the text backbone of CLIP models to do ZSC. Hence, can be lightweight + supports more languages without trading-off accuracy. (Super simple, a 10th-grader could totally write this but since no 10th-grader did, I did) - Prithivi Da

35
/ 100
Emerging

This tool helps you quickly categorize text snippets into predefined categories, even if you haven't explicitly trained a model on those categories. You input a piece of text and a list of potential labels, and it outputs the text along with the most likely labels and their scores. This is ideal for anyone who needs to sort or understand unstructured text data, such as market researchers, content moderators, or customer service analysts.

No commits in the last 6 months.

Use this if you need to classify text into categories without extensive training data, especially across multiple languages, and value a lightweight, efficient solution.

Not ideal if your text classification requires highly specialized, nuanced categories that are not well-represented by common language patterns.

text-categorization content-analysis multilingual-data weak-labeling information-extraction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

37

Forks

5

Language

Python

License

MIT

Last pushed

Apr 05, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/PrithivirajDamodaran/Alt-ZSC"

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