Developed an English to Sesotho machine translation system for the Department of Arts and Culture (DAC)

Awarded funding by the Department of Arts and Culture (DAC) for the development of English to Tshivenḓa and English to isiNdebele machine translation systems

NLP web services for resource-scarce languages which allows access to 61 core technologies


Founding member and official node of the South African Centre for Digital Language Resources (SADiLaR)

321 attendees trained in the use of Autshumato ITE software during 20 workshops

CTexTools (most downloaded resource on the RMA website) now includes core technologies developed during the NCHLT: Text phase I and II projects


Online Translation Aids: Autshumato Machine Translation Web Service, Translation Memory and Glossary Integration System and the NWU Termbank

NCHLT Corpus Portal and optical character recognition systems for South African languages

Integration of 9 Spelling Checkers and Hyphenators for South African languages

Mobile Autshumato Translate app providing automatic sentence and word translation for South African languages.

VivA offline app for Android and iOS and VivA online app for Android, iOS and Windows 10


Autshumato project awarded the Outstanding Innovation Project by the NWU's Innovation Office

Development of VivA dictionary portal for access to various dictionaries

Autshumato project received the Outstanding Innovation Project award at the Institutional Dinner for Excellence in Research

Publically available machine translation systems via software as a service

First mobile application for Android and iOS, the VivA-app


Development of language identifiers, phrase chunkers, and named-entity recognisers for 10 South African languages (Department of Arts and Culture, South Africa)

               CTexT® appointed as technology partner of the Virtuele Instituut vir Afrikaans (VivA), (Suid-Afrikaanse Akademie vir Wetenskap en Kuns, South Africa)


English to Xitsonga machine translation system as part of the Autshumato Project (Department of Arts and Culture, South Africa)

Delivery of the NCHLT: Text Resource Development Project for ten South African languages, including: corpora. annotated data and five core technologies

Consolidation of corpora for ten South African languages totalling more than 400 million words


Establishment of the Language Resource Management Agency (RMA) of the NCHLT (Department of Arts and Culture, South Africa)

CTexT® donates 1 700 language learning software units for isiXhosa, isiZulu, Afrikaans, and Setswana to African Health Placements


The Autshumato ITE selected as Softpedia’s database

MarkWrite project was awarded the “Top Upcoming Innovative Idea and Business Plan” in the NWU-Pukke’s Innovation Competition for students

WordNets for isiZulu, isiXhosa, Setswana Sesotho sa Leboa, and Afrikaans


Named NWU Top Technology Innovator at the Institutional Dinner for Excellence in Research

Appointed as the National Centre for Human Language Technology: Text Agency (Department of Arts and Culture, South Africa)

Electronic Multilingual Illustrated Dictionary, including five language-independent language games (in partnership with Pharos Dictionaries, South Africa)


Custom Terminology Management System (TMS) for terminology development in South African languages (Department of Arts and Culture, South Africa)

Tokenisers, sentence separators, and morphological decomposers for all South African languages

Collection of the NCHLT corpora consisting of government texts in 11 South African languages

Multilingual corpus development through agreements with various magazine publishers


Afrikaanse SkryfGoed 2008 with the first grammar checker for Afrikaans

Autshumato project deliverables released, including translation memories, machine translation capabilities and glossaries

Spelling checkers for ten South African languages (Department of Arts and Culture, South Africa)


Web-based word translators (TransTips) for four South African Language Pairs

Lexicon Annotation and Regulation Assistant (LARA) software for data-annotation projects

Phonetic transcription of South African place names (Acapela Group, Sweden)

Afrikaans grapheme-to-phoneme converter


Autshumato Integrated Translation Environment (ITE) and machine translation systems for three South African language pairs (Department of Arts and Culture, South Africa)

Computer-Assisted Language Learning (CALL) software for Afrikaans, isiZulu, isiXhosa, and Setswana

Spelling checkers for Hausa, Igbo, Kinyarwanda, Wolof, and Yoruba (Microsoft, Ireland)

Awarded the PanSALB Multilingualism Award for the promotion of multilingualism in South Africa by the Pan South African Language Board

Development of speech data for all South African languages (Meraka Institute, South Africa)


Awarded the Johan Kruger Prize of the South African Translators’ Institute (SATI) for significant contribution to multilingualism in the country

First commercial spelling checkers and hyphenators for isiZulu, isiXhosa, Sesotho sa Leboa, and Setswana

Afrikaanse SkryfGoed 2005 with Afrikaans thesaurus released


The Centre for Text Technology (CTexT®) established in June 2004

First commercial product launched: Afrikaanse Speltoetser 2.0 & Woordafbreker

Spelling checkers for Afrikaans, isiXhosa, isiZulu, Sesotho sa Leboa, and Setswana (Microsoft, Ireland)

Localisation of Microsoft® Windows® and Office® for Afrikaans, isiZulu, and Setswana (Microsoft, South Africa)