SADiLaR takes the lead in digitising 11 national languages

Benito Trollip, a researcher for Afrikaans at SADiLaR

Benito Trollip, a researcher for Afrikaans at SADiLaR, says the centre is a research facility with the broad purpose of promoting and stimulating all the official languages. The centre does this through research and collaboration, developing digital resources for these languages and unlocking existing sources by presenting them digitally (digitising), as well as enriching the content (digitalising).

SADiLaR is the only digital hub of its kind in Africa.

“We are committed to the development of digital humanities in Africa by promoting interdisciplinary cooperation between language, literary, computer and other experts.

“Our activities are mainly project and output-driven, with quite a number of projects running simultaneously,” Trollip says.

“SADiLaR’s involvement in and funding of projects depend directly on a thorough selection process, as well as the requirement that those who apply for projects must be associated with one of the South African universities.”

One of SADiLaR’s current projects involves the release of orthographically transcribed speech data in the 11 official languages, for use in text-to-speech systems. Parallel collections of texts have also been generated and made available for use as part of machine translation systems.

“SADiLaR also intends to make a text collection portal available that will enable searches in electronic texts, as well as a platform for postgraduate students in the humanities to disseminate their data.”

Outputs of previous projects in the form of computer software, text collections and speech recordings are available in SADiLaR’s Institutional Repository.

Visit www.sadilar.org for more information.

• SADiLaR was established in 2016 by the Department of Science and Technology, currently the Department of Science and Innovation, as a national research facility and is located at the NWU.