Text Adaptation for Mobile Digital Teletext

Small and varying screen sizes of mobile devices pose a big problem for digital Teletext service to display its content. It is difficult to display all the text information on a small screen, where page scroll or transparent page to live video is not practical. This paper presents an adaptive text extraction method which can automatically extract key information from original text and keep semantic meanings as close as possible. We combine both statistical methods and coarse coding algorithm from neural science to shorten long text sentences in terms of generalization. The experiment results show that the methods are efficient and effective.