SMRŽ, Pavel and Petr SOJKA. Word Hy-phen-ation by Neural Networks. Neural Network World. Praha: IDG Czechoslovakia, 1997, vol. 7, No 6, p. 687-695. ISSN 1210-0552.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Word Hy-phen-ation by Neural Networks
Name in Czech Dě-le-ní slov pomocí neuronových sítí
Authors SMRŽ, Pavel (203 Czech Republic) and Petr SOJKA (203 Czech Republic, guarantor).
Edition Neural Network World, Praha, IDG Czechoslovakia, 1997, 1210-0552.
Other information
Original language English
Type of outcome Article in a journal
Field of Study 20206 Computer hardware and architecture
Country of publisher Czech Republic
Confidentiality degree is not subject to a state or trade secret
WWW URL
RIV identification code RIV/00216224:14330/97:00000106
Organization unit Faculty of Informatics
Keywords (in Czech) dělení slov;neuronové sítě;backpropagation
Keywords in English hyphenation; neural networks; backpropagation
Tags backpropagation, hyphenation, neural networks
Tags International impact, Reviewed
Changed by Changed by: doc. RNDr. Petr Sojka, Ph.D., učo 2378. Changed: 22/6/2009 16:58.
Abstract
We are discussing our experiments we made when learning feedforward neural network to find possible hyphenation points in all words of given language. Neural networks show to be a good device for solving this difficult problem. The structure of the multilayer neural network used is given, together with a~discussion about training sets, influence of input coding and results of experiments done for the Czech language. We end up with pros and cons of our approach tested---hybrid architecture suitable for a~multilingual system.
PrintDisplayed: 26/7/2024 13:22