Spellchecker tool for all 10 of SA’s vernacular languages developed

North-West University. Picture: The North-West University (NWU)/Facebook

North-West University. Picture: The North-West University (NWU)/Facebook

Published Oct 8, 2022

Share

Cape Town - South Africans can now download a spelling and hyphenation checker tool for 10 of South Africa’s official languages, excluding English.

The spellchecker tool, which was developed by the Centre for Text Technology (CTexT) at North-West University, has been made available for the public to download free of charge from the South African Centre for Digital Language Resources (SADiLaR).

The spellchecker tool offers an extensive word list for Afrikaans, Ndebele, Xhosa, Zulu, Swati, Sotho, Sesotho sa Leboa, Tswana, Venda and Tsonga.

The project was funded by the Department of Science and Innovation (DSI) as part of its South African Research Infrastructure Roadmap (SARIR).

CTexT head Dr Martin Puttkamer said the tool was developed by working in close collaboration with linguists at South African universities and the national language bodies.

Puttkamer said: “We developed spelling checkers that evaluate words according to the official orthography of each language.”

The speller and hyphenation tool works with the Microsoft Office Suite allowing the user to choose their South African language in the relevant Microsoft software. It then recognises and corrects spelling, hyphenation and typing errors and suggests alternatives for words that are not recognised.

“This was done in recognition that our South African languages are under-resourced in terms of available data required for tools such as this, and that language is constantly changing and evolving.

“The tool also provides a custom dictionary to which users can add words they regularly use and are not in the tool’s existing word lists,” the team at SADiLaR said.

Adding that, the tool’s custom dictionaries can also be shared with the developer if the user chooses to do so, to be verified and included in future updates.

“SADiLaR also welcomes contributors and collaborators to help with expanding the tool’s word lists.”

SADiLaR executive director Professor Khumalo Langa said: “SADiLaR is a national research infrastructure mandated to support research and development in the domains of language technologies and language-related studies.”

Langa said: “It is thus a great triumph for us to be able to make available such a valuable tool to support multilingualism in South Africa and build up the necessary technological resources to ensure our languages remain relevant in the fourth industrial revolution.”

“We hope that making the spelling checkers freely available will help strengthen the digital presence of all our indigenous languages, facilitate the production of more digital texts in these languages, and provide access to information technology to all our citizens,” added Puttmaker.

nomalanga.tshuma@inl.co.za

Cape Argus