25/04/2020

A Design Engineering Approach for Quantitatively Exploring Context-Aware Sentence Retrieval for Nonspeaking Individuals with Motor Disabilities

Per Ola Kristensson, James Lilley, Rolf Black, Annalu Waller

Keywords: augmentative and alternative communication, design engineering, text entry, context-aware text entry, sentence prediction, information retrieval

Abstract: Nonspeaking individuals with motor disabilities typically have very low communication rates. This paper proposes a design engineering approach for quantitatively exploring context-aware sentence retrieval as a promising complementary input interface, working in tandem with a word-prediction keyboard. We motivate the need for complementary design engineering methodology in the design of augmentative and alternative communication and explain how such methods can be used to gain additional design insights. We then study the theoretical performance envelopes of a context-aware sentence retrieval system, identifying potential keystroke savings as a function of the parameters of the subsystems, such as the accuracy of the underlying auto-complete word prediction algorithm and the accuracy of sensed context information under varying assumptions. We find that context-aware sentence retrieval has the potential to provide users with considerable improvements in keystroke savings under reasonable parameter assumptions of the underlying subsystems. This highlights how complementary design engineering methods can reveal additional insights into design for augmentative and alternative communication.

The video of this talk cannot be embedded. You can watch it here:
https://www.youtube.com/watch?v=VmtD5zktNco
(Link will open in new window)
 0
 0
 0
 0
This is an embedded video. Talk and the respective paper are published at CHI 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers