Five Challenges for Intelligent Text Entry Methods

TLDR

Text entry methods must deliver high entry rates, low error rates, be easy to learn, and offer effective error correction, and intelligent methods combine AI with HCI theory to enable efficient and effortless entry. The study samples techniques from the literature, contextualizes them historically, and highlights five challenges—localization, error correction, editor support, feedback, and context of use. The author samples techniques from the literature and situates them historically.

Abstract

For text entry methods to be useful they have to deliver high entry rates and low error rates. At the same time they need to be easy to learn and provide effective means of correcting mistakes. Intelligent text entry methods combine AI techniques with human‐computer interaction (HCI) theory to enable users to enter text as efficiently and effortlessly as possible. Here I sample a selection of such techniques from the research literature and set them into their historical context. I then highlight five challenges for text entry methods that aspire to make an impact in our society: localization, error correction, editor support, feedback, and context of use.