Intelligent Tamil texting for Mobile environment
Baskaran Sankaran, Karthik Srinivasan, Ramesh Kumar S. · 2004
The limited scope of the input interface in mobile computing environment has led to the development of intelligent input mechanisms. These mechanisms can be classified into two categories - text input and graphic input. While graphic input methods are widely used in PDAs and palm pilots, text based interfaces are more appropriate for mobile communication devices. Tap-a-tap, multi-tap, predictive text input etc. are some of the popular text input mechanisms used in mobile computing devices such as simputers, PDAs and mobile phones. This paper broadly focuses on the text-based input solutions for the mobile communication devices. Messaging or more simply texting, is one of the key features in mobiles and the limitations of the telephone keypad pose a greater challenge in keying in texts. The common solution is multi-tap approach, where the characters are spread across the keypad and the user has to press the keys appropriate number of times for a specific character. The disadvantage with this approach is the slow typing, waiting time etc. Keying in a substantially long message will often result in fatigue. Several research works focused on finding a better and efficient alternative and this resulted in the predictive text input algorithms. The idea here is to use the optimized language model for intelligent texting, which improves the input speed tremendously. Predictive text input has been already developed for about 40 languages including English, Hindi and Tamil though the commercial version for Tamil is yet to be made available in any device. First, we point out the challenges in keypad design and text input methods in general and also specifically for Tamil. We then develop and demonstrate the predictive text input algorithm. We also propose to improve the predictive texting algorithm for Tamil by adding several new features such as auto completion, next word guessing etc. This paper also presents a schematic on Tamil mobile keypad taking into consideration input speed, accommodating all characters, ease of use etc. This work has practical relevance for the mobile industry and will improve the Tamil texting approach by leaps and bounds. Our schema automatically learns new words that are initially not available in the language model from the user. The algorithm will be implemented on a regular desktop computer and we hope that this can be suitably optimized for the mobile environment easily.