Sunday 21 February 2021 is a day of celebrating mother language across the globe. What does celebrating your mother language mean to you? For some it is celebrating the mere fact that language offers an avenue of communicating in a way that others understand, others will be celebrating language as a way of learning and teaching or the means of being creative and expressing yourself. There are many other reasons to celebrate one’s mother language as it forms part of your culture and of your being.
In a country such as South Africa, which boasts of 11 official languages, each community representing its different cultures, will be celebrating their languages. Looking at the greater picture language bodies and mother tongue speakers of indigenous languages are battling with the fact that their languages are under-resourced, there is no educational material in these languages and that these languages are under-developed.
To combat these issues, the government has put in efforts to develop and preserve our indigenous languages through different platforms, institutions and infrastructures, more especially through the recently established South African Centre for Digital Language Resources (SADiLaR). SADiLaR is a national research infrastructure with the core mandate to do research and to develop technologies to assist with the abovementioned problem. The Centre with 5 functional nodes work not only on various language projects to develop technologies and apps that will contribute to our multilingual country, but also create a platform for the distribution of language resources and tools to the public to aid researchers, academics and language practitioners in their research and developmental work.
The Council for Scientific and Industrial Research (CSIR) Human Language Technology (HLT) Research Group is the speech node of SADiLaR. In collaboration with Aweza they developed a unique mobile application to bridge communication barriers between healthcare providers and patients. The mobile application, AwezaMed COVID-19, features localised speech technology such as speech recognition, machine translation, and text-to-speech developed by the CSIR. The AwezaMed COVID-19 app works on any Android smartphone. It enables healthcare providers to access phrases in English, translate them in any South African official language, and then play the phrases in the selected language.
SADiLaR’s text node, the North West University’s Centre for Text Technology (CTexT), has developed spelling checkers for all South African languages. CTexT is also well known for the translation software, Autshumato, which aids language practitioners with their translation work and assists in building glossaries.
The UNISA node of SADiLaR, linked to the Department of African Languages, conducts research in African Wordnets and Multilingual Linguistic Terminology. Open access to the African Wordnet data as well as the Multilingual Linguistic Terminology, is bound to have a significant impact not only on the promotion of African languages, but also on the further development of natural language processing applications.
The Inter-institutional Centre for Language Development and Assessment (ICELDA) is set out to develop products and services concerning language testing, reading and writing, logical reasoning, basic numeracy skills, computer and information literacy skills, building corpora, and refining and validating tests and materials for the South African languages to help students and learners integrate and acculturate with ease into the academic environment.
SADiLaR’s digitisation node is at the University of Pretoria with the main function to create language resources for the African languages by digitising different kinds of language material. The digitised output will be made available on the SADiLaR platform to be utilised by researchers and developers of Human Language Technologies. The resources and data will be freely available from SADiLaR’s website.
Last but not least, the fact that SADiLaR has 11 language researchers representing South Africa’s 11 official languages is what makes this Centre even more unique. Each researcher has a mandate to enhance the visibility of each language and assist with the development of these languages. The researchers also tailor their research around the concept of Digital Humanities, where they use computational methodologies to analyse their linguistic data. Since the inception of SADiLaR we have seen these researchers strive in finding ways to develop these indigenous languages through a variety of projects and collaborations.
At the end SADiLaR’s core mandate is to do research and development in all the 11 official languages of South Africa. To pool resources and tools to move in a direction where teaching and learning in one’s mother language is not just a mere concept but becomes a reality. It is not something that the Centre can do on its own. It is a collaborative approach between the Centre, the nodes, academic institutions, educators, government departments, funders as well as the general public.
SADiLaR is a research infrastructure, which is part of the Department of Science and Innovation’s South African Research Infrastructure Roadmap (SARIR) programme. SARIR is intended to provide a strategic, rational, medium to long term framework for planning, implementing, monitoring and evaluating the provision of research infrastructures (RIs) necessary for a competitive and sustainable national system of innovation.