Five Challenges for Intelligent Text Entry Methods

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 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.

Performance and User Experience of Touchscreen and Gesture Keyboards in a Lab Setting and in the Wild

“…Participants' open comments provided for each input method included remarks such as stating instances where they could enter non-dictionary words in STK, while using the SGK the option wasn't available. This problem of OOV errors is shared among some other intelligent text entry methods that operate on word units, such as speech recognition [12].…”

“…Mobile text entry has been a topic of intense research for over two decades (see [6,12,13,19,20,27] for surveys and overviews). Text entry on touchscreen mobile devices is typically carried out using one of two intelligent text entry methods [12].…”

“…Text entry on touchscreen mobile devices is typically carried out using one of two intelligent text entry methods [12]. The first involves typing using a single finger or two thumbs on a touch tapping QWERTY keyboard.…”

Designing and evaluating text entry methods

“…century Europe already used some of the techniques we use today when crafting text entry methods, such as word frequency analysis [3]. The Areas of active research include designing text entry methods for mobile phones (see [3,5,16] for extensive overviews), video games (e.g.…”

“…The Areas of active research include designing text entry methods for mobile phones (see [3,5,16] for extensive overviews), video games (e.g. [14]), wall-sized displays (e.g.…”