Text Predictor for Lithuanian Language

被引:0
|
作者
Gelsvartas, Julius [1 ]
Simutis, Rimvydas [1 ]
Maskeliunas, Rytis [2 ]
机构
[1] Kaunas Univ Technol, Fac Elect & Elect Engn, Automat Dept, Kaunas, Lithuania
[2] Kaunas Univ Technol, Fac Informat, Dept Multimedia Engn, Kaunas, Lithuania
关键词
Text prediction; Word prediction; User interface;
D O I
10.1007/978-3-319-24770-0_39
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.
引用
收藏
页码:460 / 468
页数:9
相关论文
共 50 条