TianduoWang/DiffAug

[EMNLP 2022] Differentiable Data Augmentation for Contrastive Sentence Representation Learning. https://arxiv.org/abs/2210.16536

29
/ 100
Experimental

This project helps researchers and developers improve the quality of sentence embeddings, which are numerical representations of text that capture meaning. It takes unlabeled or labeled text data and outputs enhanced sentence representation models, which can then be used for tasks like semantic search or text similarity. This tool is for NLP researchers, machine learning engineers, and data scientists working on advanced text understanding.

No commits in the last 6 months.

Use this if you are building or fine-tuning models for natural language understanding and need to create higher-quality, more robust sentence embeddings.

Not ideal if you are looking for a pre-packaged, ready-to-use API for sentence embeddings without needing to train or fine-tune models.

natural-language-processing machine-learning-engineering text-understanding information-retrieval semantic-search
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

40

Forks

2

Language

Python

License

MIT

Last pushed

Nov 01, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/TianduoWang/DiffAug"

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