Word Hy-phen-ation by Neural Networks

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.

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

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

20206 Computer hardware and architecture

Country of publisher

Czech Republic

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

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

---

Abstract

V originále

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.