Type, Then Correct: Intelligent Text Correction Techniques for Mobile Text Entry Using Neural Networks

Zhang, Mingrui Ray; He, Wen; Wobbrock, Jacob O.

doi:10.1145/3332165.3347924

Cited by 23 publications

(16 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…JustCorrect removes these manual operations. As we demonstrate, our study shows that saving these additional manual operations signifcantly improves post hoc text correction speed over the "Type, then Correct" technique [42].…”

Section: Error Correction Techniques On Smartphonesmentioning

confidence: 60%

“…Finally, (3) we integrated both JustCorrect-Tap and JustCorrect-Gesture into a soft keyboard. Our evaluation shows that using JustCorrect reduces post hoc text correction time by 12.8% over the stock Android keyboard, which uses de facto cursor-based text correction, and by 9.7% over TTC [42]. Overall, our research shows JustCorrect complements existing post hoc text correction techniques and makes text correction more automatic and intelligent than prior techniques.…”

Section: Introductionmentioning

confidence: 72%

“…The "Type, then Correct" technique [42] is a recent effort at reducing cursor operations by injecting intelligence into the post hoc text correction process. To correcct an error, a user types a correction word and either: (1) "throws" the word from the suggestion bar towards the error, or (2) drags their fnger atop a designated "Magic Key" to navigate among highlighted error candidates, pressing the key to commit the correction.…”

Section: Error Correction Techniques On Smartphonesmentioning

confidence: 99%

“…Our experiment included two studies. The frst study compared JustCorrect Keyboard with the stock Android Keyboard with cursor-based method, while the second study compared JustCorrect Keyboard with the recently published "Type, then Correct" (TTC) keyboard [42]. The two studies were almost identical except for the levels of independent variable and participants.…”

Section: Experiments 2: Evaluating Justcorrect Key-boardmentioning

confidence: 99%

“…The de facto cursorbased text correction technique requires accurately positioning the cursor at the error text, repeatedly pressing backspace to delete errors, and re-positioning the cursor back at its original location. The recent "Type, then Correct" technique (TTC) [42] eliminated these cursor control operations by (1) letting the user "throw" the correction at the error text, or (2) pressing a key to locate error candidates and eventually commit the correction. However, TTC still requires users to specify the correction location.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

JustCorrect

Cui

Zhu

Zhang

et al. 2020

Proceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology

Self Cite

View full text Add to dashboard Cite

Correcting errors in entered text is a common task but usually diffcult to perform on mobile devices due to tedious cursor navigation steps. In this paper, we present JustCorrect, an intelligent post hoc text correction technique for smartphones. To make a correction, the user simply types the correct text at the end of their current input, and JustCorrect will automatically detect the error and apply the correction in the form of an insertion or a substitution. In this way, manual navigation steps are bypassed, and the correction can be committed with a single tap. We solved two critical problems to support Just-Correct: (1) Correction Algorithm: we propose an algorithm that infers the user's correction intention from the last typed word. (2) Input Modalities: our study revealed that both tap and gesture were suitable input modalities for performing Just-Correct. Based on our fndings, we integrated JustCorrect into a soft keyboard. Our user studies show that using JustCorrect reduces the text correction time by 12.8% over the stock Android keyboard and by 9.7% over the "Type, then Correct" text correction technique by Zhang et al. (2019). Overall, JustCorrect complements existing post hoc text correction techniques, making error correction more automatic and intelligent.

show abstract

Section: Error Correction Techniques On Smartphonesmentioning

confidence: 60%

Section: Introductionmentioning

confidence: 72%

Section: Error Correction Techniques On Smartphonesmentioning

confidence: 99%

Section: Experiments 2: Evaluating Justcorrect Key-boardmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations