Probabilistic Text Entry-Case Study 3

Home > Publications > Probabilistic Text Entry-Case Study 3

Probabilistic Text Entry-Case Study 3

Keith Vertanen

Intelligent Computing for Interactive System Design: Statistics, Digital Signal Processing, and Machine Learning in Practice, 2021.

The reading and writing of text is an activity that has long dominated our interactions with computers. Early user interfaces often displayed only text and relied on input obtained via a desktop keyboard. Actions on the keyboard were deterministic; if you hit a particular key, the action linked to that key was immediately triggered. Today, most of our desktop keyboard interactions retain this predictability with a few exceptions such as the automatic spelling correction of some word processors. However, using a desktop keyboard may not always be desirable or practical. For example, we may be away from our desk and need to enter text on a mobile device. We may want to enter text in new computing environments such as virtual reality (VR), augmented reality (AR), or in environments embedded with sensors and displays (e.g. autonomous cars). This chapter looks at the techniques and challenges associated with moving away from our trusty desktop keyboard to input methods that are inherently uncertain.