Welcome to the South African Centre for Digital Language Resources website
Log In

Log In

Forgot Your Password?

Tray Subtotal: R0.00

CSIR Human language technology and language resource audit

The first Human Language Technology (HLT) Audit in South Africa was conducted in 2009. Eight years later, noting the increased activity in the HLT field, an increase in the number of institutions conducting HLT research and the introduction of digital humanities in South Africa, the Human Language Technology Research Group (HLTRG) at the CSIR Meraka Institute is conducting a follow-up Audit. This Audit is being conducted under the auspices of the South African Centre for Digital Language Resources (SADiLaR).

To participate in the audit, please contact Ilana Wilken (iwilken@csir.co.za) for more information and access to the audit.

The objectives of this Audit are:

1. To provide a systematic and detailed inventory of the current HLT components (software, models) and resources (data) for the official South African languages;

2. To set out the most important dimensions/criteria for the documentation of the HLT components and language resources;

3. To describe the status of the HLT components and language resources in the SA R&D environment for the 11 official languages:

  • Which components and resources exist and are freely available?
  • Which components and resources are most important for the SA context?
  • What differences exist in components and resources across the 11 official languages? and

4. To indicate the gaps between available components/resources and the most important components/resources for the South African context.

The information emanating from the Audit will be collated and displayed on the SADiLaR website, in the form of a catalogue of resources available for download, and a list of resources known to exist but not available for download (to see what is currently available, click here: https://rma.nwu.ac.za/). This information will make it possible for South African language-related research endeavours to be enhanced through collaboration between researchers interested in similar topics, through reusing/repurposing available resources, by extending available resources, and by reducing duplication.