steph-jung/GenieType

Implementation of Federated Learning For Mobile Keyboard Prediction: https://arxiv.org/abs/1811.03604

26
/ 100
Experimental

This project helps improve the prediction accuracy of mobile keyboards without compromising user privacy. It takes your typing data (what you type and how you type it) and collectively learns better next-word suggestions. Mobile keyboard users who value both convenience and data privacy would use this.

No commits in the last 6 months.

Use this if you want your mobile keyboard to get smarter at predicting words without sending your personal typing habits to a central server.

Not ideal if you prefer a keyboard that operates solely on a local dictionary or if you are not concerned with sharing your typing data for cloud-based improvements.

mobile-keyboard predictive-text user-privacy text-entry smartphone-usability
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

10

Forks

2

Language

Jupyter Notebook

License

Last pushed

Jun 25, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/steph-jung/GenieType"

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