JohnGiorgi/DeCLUTR

The corresponding code from our paper "DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations". Do not hesitate to open an issue if you run into any trouble!

41
/ 100
Emerging

This project helps machine learning engineers or data scientists create high-quality, general-purpose text embeddings without needing manually labeled data. You provide a large collection of unlabeled documents, and it processes them to output numerical representations (embeddings) that capture the meaning of your text. These embeddings can then be used for tasks like semantic search, clustering, or text similarity.

378 stars. No commits in the last 6 months.

Use this if you need powerful, unlabeled text embeddings for downstream natural language processing tasks and want to train your own models from scratch or fine-tune existing ones.

Not ideal if you already have labeled data for your specific task or if you only need pre-trained embeddings without custom training.

natural-language-processing unsupervised-learning text-analytics machine-learning-engineering text-representation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

378

Forks

33

Language

Python

License

Apache-2.0

Last pushed

Apr 21, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/JohnGiorgi/DeCLUTR"

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