A Connectionist Technique for Accelerated Textual Input: Letting a Network Do the Typing

Each yearpeoplespendahugeamountoftimetyping. Thetextpeopletype typically contains a tremendousamount of redundancy due to predictable word usage patterns and the text's structure. This paper describes a neural networksystemcallAuto'Qpistthat monitorsaperson's typingand predicts what will be entered next. Auto'Qpist displays the most likely subsequent word to the typist, who can accept it with a single keystroke, instead of typing it in its entirety. The multi-layerperceptron at the heart of Auto'Qpist adapts its predictionsof likelysubsequenttext to the user's word usage pattern, and to the characteristicsof the text currently being typed. Increases in typing speed of 2-35 when typingEnglish prose and 10-208 when typing C code have been demonstrated using the system, suggestinga potentialtimesavingsofmorethan 20hoursper user peryear. In addition to increasingtyping speed,AutoTypistreduces the number of keystrokes a user must type by a similar amount (2-35...

• Type: Conference
• Year: 1994
• Where: NIPS
• Authors: Dean Pomerleau
• Keywords: NIPS 1994, NIPS 2007, Predictable Word Usage, Typing, Word Usage Pattern