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

Uses contrastive learning with span-based data augmentation to train sentence encoders on unlabeled text, requiring only documents and no labeled data. Implements mean-pooled RoBERTa-based transformers optimized via a contrastive objective, integrated with AllenNLP training infrastructure and compatible with Hugging Face model export. Evaluated extensively on SentEval downstream and probing tasks, achieving competitive performance without supervised pretraining.

378 stars. No commits in the last 6 months.

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.