SHARK2: a large vocabulary shorthand writing system for pen-based computers

By Per Ola Kristensson, Shumin Zhai. ACM Symposium on User Interface Software and Technology, 2004

364 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Long short term memory neural network for keyboard gesture decoding (2015, background): “In a different strand of research, methods for keyboard gesture recognition, and more generally, gesture recognition have been largely reliant on geometric distance techniques [4, 5], HMMs [14] or Dynamic Time Warping [15], among others.”
Neural Networks for Text Correction and Completion in Keyboard Decoding (2017, methodology): “We use the smaller spoken English language Twitter Typo dataset of corrected tweets [18] 2 to induce noise in the larger conversational Open SubTitles dataset 2009 [19] of 50000 unique words, by modelling the noise distribution over the Twitter data.”
Gestures without libraries, toolkits or training: a $1 recognizer for user interface prototypes (2007, methodology): “However, in mentioning this choice, the SHARK paper [11] provided no specifics as to the comparative performance of these techniques.”
Accelerating Text Communication via Abbreviated Sentence Input (2021, background): “Text entry interfaces often use a probabilistic decoder to infer a user’s text from time sequence data (Vertanen et al., 2015; Kristensson and Zhai, 2004; Zhai et al., 2002; Zhai and Kristensson, 2008).”