An overview of Sesotho BLARK content

Abstract

This article overviews digital language resources available for Sesotho, an official language of South Africa. The South African Center for Digital Language Resources (SADiLaR) repository is used as a reference as it is the official host of various language resources for South African languages. A total of 18 written resources are identified from the repository, and a further 16 spoken resources are identified. Finally, a total of 45 applications and modules were identified. Findings indicate that the majority of applications and modules available for Sesotho are in fact general resources aimed at all eleven official South African languages. Furthermore, the available resources indicate an inclination to the development of entry level, basic language resources and an absence of middle and higher resources with functionalities such as semantic analyses for written resources and prosody prediction for spoken resources. The study is hindered by the dearth of resource specific evaluations and related research and exacerbated by the absence of some of the resources on the repository.