Text Predictor for Lithuanian Language
This paper describes the architecture of the open source text prediction package Presage. We trained the n-gram model used in the text predictor for Lithuanian language. The predictor was trained and evaluated using sixteen Lithuanian literature books. Each book was split into training and test sets containing 30 % and 70 % of words. The trained text predictor was integrated into a multifunctional user interface for disabled people to improve the text input speed.
KeywordsText prediction Word prediction User interface
This research was funded by a grant QUADRIBOT, from the Agency for Science, Innovation and Technology (MITA), Lithuania.
- 2.Vescovi, M.: Soothsayer: un Sistema Multi-sorgente per la Predizione del Testo (Soothsayer: multi-source text prediction system), Milan (2004)Google Scholar
- 3.Gelšvartas, J., Simutis, R., Maskeliūnas, R.: Multifunctional user interface to control robotic arm for paralyzed people. In: Electrical and Control Technologies, p. 22 (2014)Google Scholar
- 7.Wandmacher, T., Antoine, J.Y.: Methods to integrate a language model with semantic information for a word prediction component (2008). arXiv:0801.4716
- 8.Van Den Bosch, A.: Scalable classification-based word prediction and confusible correction. Traitement Automatique des Langues 46(2), 39–63 (2006)Google Scholar
- 9.Mikolov, T., Yih, W.T., Zweig, G.: Linguistic regularities in continuous space word representations. In: HLT-NAACL, pp. 746–751 (2013)Google Scholar