Spatial model personalization in Gboard
Gary Sivek, Michael Riley

TL;DR
This paper presents a personalized spatial model for Gboard that adapts to individual user behavior, improving typing speed and accuracy through real-world data and clustering techniques.
Contribution
It introduces a method for personalizing a Gaussian spatial model in Gboard using user-specific key offsets and covariances, validated with real-world data.
Findings
Improved typing speed and accuracy across multiple languages.
Effective personalization with real user data.
Optimal clustering reduces overfitting.
Abstract
We introduce a framework for adapting a virtual keyboard to individual user behavior by modifying a Gaussian spatial model to use personalized key center offset means and, optionally, learned covariances. Through numerous real-world studies, we determine the importance of training data quantity and weights, as well as the number of clusters into which to group keys to avoid overfitting. While past research has shown potential of this technique using artificially-simple virtual keyboards and games or fixed typing prompts, we demonstrate effectiveness using the highly-tuned Gboard app with a representative set of users and their real typing behaviors. Across a variety of top languages, we achieve small-but-significant improvements in both typing speed and decoder accuracy.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
