Word Hy-phen-a-tion by Neural Networks

SMRŽ, Pavel and Petr SOJKA. Word Hy-phen-a-tion by Neural Networks. 1996. FIMU-RS-96-04.

Basic information

Original name

Word Hy-phen-a-tion by Neural Networks

Authors

SMRŽ, Pavel (203 Czech Republic) and Petr SOJKA (203 Czech Republic, guarantor)

Edition

FIMU-RS-96-04, 1996

---

Other information

Language

English

Type of outcome

Audiovizuální tvorba

Field of Study

20200 2.2 Electrical engineering, Electronic engineering, Information engineering

Country of publisher

Czech Republic

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

Abstract PostScript PDF

RIV identification code

RIV/00216224:14330/96:00030432

Organization unit

Faculty of Informatics

Keywords in English

neural networks;hyphenation

Tags

hyphenation, neural networks

---

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.