Original Research

Neural networks as possible hyphenation technique for Afrikaans

Machteld Fick
Suid-Afrikaanse Tydskrif vir Natuurwetenskap en Tegnologie | Vol 22, No 1 | a203 | DOI: https://doi.org/10.4102/satnt.v22i1.203 | © 2003 Machteld Fick | This work is licensed under CC Attribution 4.0
Submitted: 26 September 2003 | Published: 26 September 2003

About the author(s)

Machteld Fick, Departement Kwantitatiewe Bestuur, Universiteit van Suid-Afrika, South Africa

Full Text:

PDF (342KB)

Share this article

Bookmark and Share

Abstract

In Afrikaans compound words are written as one word. New words are therefore created by simply joining words. Word hyphenation during typesetting by computer is often a problem, because the source of reference changes all the time. A neural network (feedforward backpropagation) was trained with about 5 000 Afrikaans words with correct syllabification. The neural network classified 97,56% of possible points in 5 000 randomly chosen words correctly as either valid or invalid hyphenation points. In a test with 510 words from an Afrikaans magazine the neural network classified 98,75% of possible positions correctly. We came to the conclusion that neural networks can be used successfully as hyphenation technique for Afrikaans.


Keywords

No related keywords in the metadata.

Metrics

Total abstract views: 2137
Total article views: 2189

Reader Comments

Before posting a comment, read our privacy policy.

Post a comment (login required)

 

Crossref Citations

1. Viability of Neural Networks for Core Technologies for Resource-Scarce Languages
Melinda Loubser, Martin J. Puttkammer
Information  vol: 11  issue: 1  first page: 41  year: 2020  
doi: 10.3390/info11010041