Title :
A neural network approach to hyphenating Norwegian
Author :
Kristensen, Terje
Author_Institution :
Dept. of Comput. Sci., Bergen Univ. Coll., Landas, Norway
Abstract :
This paper presents a method to automatically hyphenate Norwegian by a backpropagation neural network. The original database consists of about 67000 Norwegian words and is developed by the Norwegian Computing Centre for the Humanities at the University of Bergen. The experiments have been done on a PC-platform and on only a sample of words from the database. The hyphenation program has been developed in Cortex-Pro, a general purpose neural network simulation environment
Keywords :
backpropagation; database management systems; microcomputer applications; neural nets; text editing; Cortex-Pro; Norwegian; PC-platform; backpropagation neural network; database; hyphenation; Backpropagation; Computational modeling; Computer science; Databases; Dictionaries; Educational institutions; Electronic mail; Logic; Neural networks; Pattern matching;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.857889
