aonotas/adversarial_text

Code for Adversarial Training Methods for Semi-Supervised Text Classification

38
/ 100
Emerging

This project provides code to apply advanced adversarial training techniques for classifying text, even when you have limited labeled data. It takes in text documents and a small set of labeled examples, along with a larger pool of unlabeled text, to produce a robust text classification model. This is useful for machine learning engineers or researchers who are developing text-based AI solutions.

124 stars. No commits in the last 6 months.

Use this if you need to build highly accurate text classifiers, especially when only a small portion of your training data is hand-labeled.

Not ideal if you are looking for an out-of-the-box solution with a user interface, as this requires familiarity with machine learning frameworks and command-line execution.

text-classification semi-supervised-learning natural-language-processing machine-learning-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 20 / 25

How are scores calculated?

Stars

124

Forks

28

Language

Python

License

Last pushed

Jul 10, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/aonotas/adversarial_text"

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