The Department of African Languages at UNISA is committed to the promotion, development and use of the South African languages. The Department conducts research that contributes to the advancement of knowledge of African languages, promotes scholarship in African languages and serves as a partner by reaching out to the community through its expertise in African languages.
The UNISA node is currently working on two subprojects that will provide valuable language resources for the empowerment of the African Languages within SADiLaR.
African Wordnet (AWN) subproject:
This subproject is a continuation of three previous phases of Wordnet development for five African languages that was done as a collaborative project between the Department of African Languages at UNISA and CTexT at the North-West University. A Wordnet is a lexical database consisting of words that are grouped into sets of synonyms called synsets. Various conceptual-semantic and lexical relations are indicated between the synsets contained in a Wordnet. Wordnets are fundamental resources required for the development of a large number of language technologies (LTs) and LT applications. Wordnets are indispensable components of large, automatic, language-understanding systems being developed and tested in academia and industry. Adding South African languages to the Wordnet database will enable the development of various applications for each of these languages, while also being a valuable research resource.
During the next phase of the project, the development team will focus on adding new synsets, usage examples, and definitions to the current version of the AWN. As a basis for this extension of the Wordnets, this phase of the project will use the SIL Comparative African Wordlist (see https://www.eva.mpg.de/lingua/tools-at-lingboard/pdf/Snider_silewp2006-005.pdf) in order to ensure comparable development in all five languages. Representation of all 1 700 words in this list in the AWN will ensure a broad coverage of concepts shared among most African languages. This will lead to a useful resource not only for comparative purposes but also for language learners, and in particular for further development of other tools in the digital humanities.
Linguistic terminology subproject:
Specialised, multilingual terminology lists play a vital role in the South African environment, by enabling users to find very specific information in a structured, user-friendly manner. This subproject aims to create a term bank to encapsulate linguistic terminology often used in academic texts. The idea was conceptualised from the realisation that there is a wealth of existing linguistic terminology in African languages that is contained in discontinued and out-of-print hard copy publications. Unfortunately, their current format restricts accessibility to the knowledge represented in them. There is a pressing need to preserve and develop electronic versions of these resources to improve their accessibility.
This subproject is based on the incomplete SAMTerm (multilingual linguistics terminology database) which was conceptualised mainly for the purpose of teaching and learning in the Department of African Languages at UNISA, but also for use by researchers and other language practitioners such as translators. The subproject will be linked to the Open Educational Resource Term Bank of the University of Pretoria (UP) and will also benefit from the digitisation and term extraction capacity of UP.