Förenklad textinmatning på mobila enheter med hjälp av kontextbaserad språktolkning
InformationsteknikTextinmatningSmsMobiltelefonKontextmodelleringTextmeddelandeBegränsad knappsatsSpråkmodelleringViterbiavkodningInformationsteknik
The number of text messages sent from mobile phones, has increased dramatically over the last few years. Along with that, we are witnessing a lot of new mobile portal services currently being developed. Many of these services rely on an ability to input text efficiently. The traditional phone keypad is ambiguous because each key encodes more than one letter. At present, the most common way to deal with this problem is using a stored dictionary to guess the intended input. This thesis presents a new text entry strategy called Qtap. Instead of using a stored dictionary to guess the intended word, this method uses probabilities of letter sequences. New features that come with Qtap are the usage of the viterbi algorithm to decode input sequences and a non-alphabetic keypad. How the strategy and the keypad used by Qtap were developed, is described throughout the thesis. Qtap is also compared to a dictionary-based method, t9, on a non-user level. The results show Qtap is performing well in many senses. The conclusion from this is that a further development of Qtap is motivated. A discussion of various modifications and additions to the design, that may yield a performance improvement, is also included.