AI-Driven Intelligent Text Correction Techniques for Mobile Text Entry

Mingrui Ray Zhang; He Wen; Wenzhe Cui; Suwen Zhu; H. Andrew Schwartz; Xiaojun Bi; Jacob O. Wobbrock

doi:10.1007/978-3-030-82681-9_5

AI-Driven Intelligent Text Correction Techniques for Mobile Text Entry

Mingrui Ray Zhang
, He Wen
, Wenzhe Cui
, Suwen Zhu
, H. Andrew Schwartz
, Xiaojun Bi
, Jacob O. Wobbrock

Computer Science

University of Washington
Carnegie Mellon University
Stony Brook University
Grammarly

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

5 Scopus citations

Abstract

Current text correction processes on mobile touch devices are laborious: users either extensively use backspace, or navigate the cursor to the error position, make a correction, and navigate back, usually by employing multiple taps or drags over small targets. In this chapter, we present two techniques, Type, Then Correct and JustCorrect, that utilize the power of artificial intelligence to improve the text correction experience on mobile devices. All of the techniques skip error-deletion and cursor-positioning procedures, and instead allow the user to type the correction first, and then apply that correction to a previously committed error. We evaluated these techniques in and the results show that correction with the new techniques was faster than de facto cursor and backspace-based correction.

Original language	English
Title of host publication	Human - Computer Interaction Series
Publisher	Springer International Publishing
Pages	131-168
Number of pages	38
DOIs	https://doi.org/10.1007/978-3-030-82681-9_5
State	Published - 2021

Publication series

Name	Human - Computer Interaction Series
Volume	Part F10072
ISSN (Print)	1571-5035
ISSN (Electronic)	2524-4477

Access to Document

10.1007/978-3-030-82681-9_5

Cite this

@inbook{8c1f4a323470422a868b325ac7f6aa06,

title = "AI-Driven Intelligent Text Correction Techniques for Mobile Text Entry",

abstract = "Current text correction processes on mobile touch devices are laborious: users either extensively use backspace, or navigate the cursor to the error position, make a correction, and navigate back, usually by employing multiple taps or drags over small targets. In this chapter, we present two techniques, Type, Then Correct and JustCorrect, that utilize the power of artificial intelligence to improve the text correction experience on mobile devices. All of the techniques skip error-deletion and cursor-positioning procedures, and instead allow the user to type the correction first, and then apply that correction to a previously committed error. We evaluated these techniques in and the results show that correction with the new techniques was faster than de facto cursor and backspace-based correction.",

author = "Zhang, \{Mingrui Ray\} and He Wen and Wenzhe Cui and Suwen Zhu and \{Andrew Schwartz\}, H. and Xiaojun Bi and Wobbrock, \{Jacob O.\}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.",

year = "2021",

doi = "10.1007/978-3-030-82681-9\_5",

language = "English",

series = "Human - Computer Interaction Series",

publisher = "Springer International Publishing",

pages = "131--168",

booktitle = "Human - Computer Interaction Series",

}

TY - CHAP

T1 - AI-Driven Intelligent Text Correction Techniques for Mobile Text Entry

AU - Zhang, Mingrui Ray

AU - Wen, He

AU - Cui, Wenzhe

AU - Zhu, Suwen

AU - Andrew Schwartz, H.

AU - Bi, Xiaojun

AU - Wobbrock, Jacob O.

PY - 2021

Y1 - 2021

N2 - Current text correction processes on mobile touch devices are laborious: users either extensively use backspace, or navigate the cursor to the error position, make a correction, and navigate back, usually by employing multiple taps or drags over small targets. In this chapter, we present two techniques, Type, Then Correct and JustCorrect, that utilize the power of artificial intelligence to improve the text correction experience on mobile devices. All of the techniques skip error-deletion and cursor-positioning procedures, and instead allow the user to type the correction first, and then apply that correction to a previously committed error. We evaluated these techniques in and the results show that correction with the new techniques was faster than de facto cursor and backspace-based correction.

AB - Current text correction processes on mobile touch devices are laborious: users either extensively use backspace, or navigate the cursor to the error position, make a correction, and navigate back, usually by employing multiple taps or drags over small targets. In this chapter, we present two techniques, Type, Then Correct and JustCorrect, that utilize the power of artificial intelligence to improve the text correction experience on mobile devices. All of the techniques skip error-deletion and cursor-positioning procedures, and instead allow the user to type the correction first, and then apply that correction to a previously committed error. We evaluated these techniques in and the results show that correction with the new techniques was faster than de facto cursor and backspace-based correction.

UR - https://www.scopus.com/pages/publications/105036528141

U2 - 10.1007/978-3-030-82681-9_5

DO - 10.1007/978-3-030-82681-9_5

M3 - Chapter

AN - SCOPUS:105036528141

T3 - Human - Computer Interaction Series

SP - 131

EP - 168

BT - Human - Computer Interaction Series

PB - Springer International Publishing

ER -

AI-Driven Intelligent Text Correction Techniques for Mobile Text Entry

Abstract

Publication series

Access to Document

Other files and links

Fingerprint

Cite this