Department of Science, Technology and InnovationCLARIN in South Africa

Multilingual spelling checker lexicons

Loading...
Thumbnail Image

Date

2022-06-30

Authors

Centre for Text Technology, CTexT®

Journal Title

Journal ISSN

Volume Title

Publisher

CTexT® (Centre for Text Technology)

Abstract

Description

Spelling checker lexicons for 10 South African languages. Lexicons created by collecting data from various sources and manually reviewed by language experts according to the standard written orthography. For each language there are four different lexicon files: abbreviations..txt abbreviations and abbreviation compounds. lowercase..txt words that are correct when written in lower case. offensive..txt words that are potentially offensive, obscene, racist, or should not be suggested by a spelling checker for some other reason. uppercase..txt words that should only be written with one or more capitalised characters, such as person and place names.

Citation

License

Creative Commons Attribution 4.0 International

Verification status

Level 0