Smartphones have become vital devices in the current on-the-go Thai culture. Typically, virtual keyboards serve as tools for text input on smartphones. Due to the limited screen area and the large number of Thai characters, the size of each button on the keyboard is quite small. This leads to character mistyping and low typing speed. In this paper, we present a typical framework of a Thai Input Method on smartphones which includes four processes; Character Candidate Generation, Word Candidate Generation, Word Candidate Display, and Model Update. This framework not only works with Thai, it works with other letter-based languages as well. We also review virtual keyboards and techniques currently used and available for Thai text input.

While classification techniques can be applied for automatic unknown word recognition in a language without word boundary, it faces with the problem of unbalanced datasets where the number of positive unknown word candidates is dominantly smaller than that of negative candidates. To solve this problem, this paper presents a corpus-based approach that introduces a so-called group-based ranking evaluation technique into ensemble learning in order to generate a sequence of classification models that later collaborate to select the most probable unknown word from multiple candidates. Given a classification model, the group-based ranking evaluation (GRE) is applied to construct a training dataset for learning the succeeding model, by weighing each of its candidates according to their ranks and correctness when the candidates of an unknown word are considered as one group. A number of experiments have been conducted on a large Thai medical text to evaluate performance of the proposed group-based ranking evaluation approach, namely V-GRE, compared to the conventional naive Bayes classifier and our vanilla version without ensemble learning. As the result, the proposed method achieves an accuracy of 90.930.50% when the first rank is selected while it gains 97.260.26% when the top-ten candidates are considered, that is 8.45% and 6.79% improvement over the conventional record-based naive Bayes classifier and the vanilla version. Another result on applying only best features show 93.930.22% and up to 98.85 0.15% accuracy for top-1 and top-10, respectively. They are 3.97% and 9.78% improvement over naive Bayes and the vanilla version. Finally, an error analysis is given.