Host: The Japanese Society for Artificial Intelligence
Name : 34th Annual Conference, 2020
Number : 34
Location : Online
Date : June 09, 2020 - June 12, 2020
Typing on a on-screen keyboard is the key user interaction for communication on mobile devices. Due to the limited screen size, input error happens frequently and error correction is needed to ameliorate the typing experience. In this paper, we improve the error correction framework for QWERTY layout by utilizing the positional information from touch point coordinates. During input process, each key button will obtain a dynamic touchable region based on multiple features. Our experiments show that the proposed method reduces the input cost comparing with existing methods for multiple languages.