LiteSSLHub/DisCo

This is the public repository of EMNLP 2023 paper "DisCo: Co-training Distilled Student Models for Semi-supervised Text Mining"

16
/ 100
Experimental

DisCo helps data scientists and NLP researchers perform text mining tasks like classification or summarization using significantly smaller and faster models. It takes your existing labeled and unlabeled text data, along with a larger pre-trained language model, and outputs multiple fine-tuned, lightweight models. These models achieve comparable performance to their larger counterparts but require less computational power and inference time.

No commits in the last 6 months.

Use this if you need to deploy text mining models on resource-constrained environments or want to speed up inference without sacrificing significant performance, especially when labeled data is limited.

Not ideal if you prioritize maximum possible accuracy above all else and have abundant computational resources and labeled data, as larger, un-distilled models might offer marginal performance gains.

text-classification extractive-summarization natural-language-processing model-optimization semi-supervised-learning
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

62

Forks

Language

Python

License

Last pushed

Dec 30, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/LiteSSLHub/DisCo"

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