主催: The Japanese Society for Artificial Intelligence
会議名: 第34回全国大会(2020)
回次: 34
開催地: Online
開催日: 2020/06/09 - 2020/06/12
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.