microsoft/AMOS

[ICLR 2022] Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

30
/ 100
Emerging

This is a developer tool designed for researchers and engineers working on natural language processing. It provides scripts to fine-tune pre-trained text encoders, which are foundational components for understanding human language. You input raw text data and a text encoder model, and the output is a more accurate, specialized text encoder ready for specific language tasks.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher developing advanced natural language understanding systems and need to fine-tune state-of-the-art text encoder models for specific language tasks like sentiment analysis, question answering, or text entailment.

Not ideal if you are an end-user needing to perform language tasks without coding or model development.

natural-language-processing machine-learning-engineering text-analytics deep-learning nlp-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

26

Forks

2

Language

Python

License

MIT

Last pushed

Jul 26, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/microsoft/AMOS"

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