South African National Centre for Digital Language Resources

South African Centre for Digital Language Resources Justus C Roux Research Unit: Languages and Literature in the South African Context North-West University Potchefstroom Campus South Africa justus.roux@nwu.ac.za Abstract This presentation introduces the imminent establishment of a new language resource infrastructure particularly focusing on languages spoken in Southern Africa, but with an eventual aim to become a hub for digital language resources within Sub-Saharan Africa. The Constitution of South Africa makes provision for 11 official languages, with equal status although they differ significantly with regard to the number of speakers. The current language Resource Management Agency (RMA) will be merged with the new Centre, which will have a much wider focus than that of data acquisition, management and distribution. The Centre (SADiLaR) will entertain two main programs: Digitisation and Digital Humanities. The digitisation program will focus on the systematic digitisation of relevant text, speech and multi-modal data across the official languages. Relevancy will be determined by a Scientific Advisory Board. This will take place on a continuous basis through specified projects allocated to national members of the Centre, as well as through open-calls aimed at the academic as well as local communities. The digital resources will be enhanced, managed and distributed through a dedicated web-based portal. The development of the Digital Humanities (DH) program will entail extensive academic support for projects implementing digital language based data. SADiLaR will function as an enabling research infrastructure primarily supported by national government. Keywords: infrastructure, digitisation, African languages 1. Introduction The Constitution of South Africa makes provision for 11 official languages, which comprise English, Afrikaans, isiZulu, isiXhosa, Siswati, isiNdebele, Sesotho, Setswana, Sesotho sa Lebowa (Northern Sotho), Tshivenda and Xitsonga. Figure 1 below depicts the balance between the different languages: Figure 1 Home languages in South Africa (n=54 mil.) Apart from English, all of the other languages are regarded as resource scarce languages. This obviously calls for actions to develop resources for these languages, preferably in a coordinated and systematic manner. 2. Building a resource infrastructure In 2008 a proposal to establish a National Centre for Human Technologies (HLT) was approved by Cabinet of National Government with the intent, inter alia, to develop applicable language resources. In practice, this became a virtual (administrative) centre under the auspices of the HLT Unit within the Department of Arts and Culture (DAC). A ministerial expert panel on HLT (HLTEP) currently assists the HLT Unit to develop strategic plans and fund development projects in the HLT domain. As funding for HLT projects became available from the DAC and also from the Department of Science and Technology (DST), the necessity for a central repository for reusable language resources became crucial. In 2012 the DAC then set up a language Resource Management Agency (RMA) which is currently being run by the Centre for Text Technology (CTexT©) at the North-West University in Potchefstroom (http://www.rma.nwu.ac.za). Since its inception four years ago, the RMA has shown significant growth in the number of clients and in the distribution of language resources, including applicable software for various …

Content truncated to 500 words