Private federated discovery of out-of-vocabulary words for Gboard

The vocabulary of language models in Gboard, Google's keyboard application, plays a crucial role for improving user experience. One way to improve the vocabulary is to discover frequently typed out-of-vocabulary (OOV) words on user devices. This task requires strong privacy protection due to th...

Full description

Saved in:
Bibliographic Details
Main Authors Sun, Ziteng, Kairouz, Peter, Sun, Haicheng, Gascon, Adria, Suresh, Ananda Theertha
Format Journal Article
LanguageEnglish
Published 17.04.2024
Subjects
Computer Science - Data Structures and Algorithms
Online AccessGet full text

Cover

More Information
Summary:The vocabulary of language models in Gboard, Google's keyboard application, plays a crucial role for improving user experience. One way to improve the vocabulary is to discover frequently typed out-of-vocabulary (OOV) words on user devices. This task requires strong privacy protection due to the sensitive nature of user input data. In this report, we present a private OOV discovery algorithm for Gboard, which builds on recent advances in private federated analytics. The system offers local differential privacy (LDP) guarantees for user contributed words. With anonymous aggregation, the final released result would satisfy central differential privacy guarantees with $\varepsilon = 0.315, \delta = 10^{-10}$ for OOV discovery in en-US (English in United States).
DOI:10.48550/arxiv.2404.11607