Digitizing African languages: Building a Digital Lexicon

Abstract

Africa is a linguistic paradise that has about one third of the world‘s languages within its borders. Nigeria alone is home to over four hundred and fifty languages. Despite the multiplicity of languages, many of them are minority languages: unwritten and undocumented. However, African languages do not have to remain as only languages of oral communication. The increased use of digital technology in the world today buttresses the need to digitize African languages as this would enable access, research, and sharing across the globe on various digital platforms. This paper outlines texts, pictures, audio and video as the kinds of digital data that can be created for African languages. It describes four steps for building a digital lexicon that can be published online, (on the web and on mobile phones) namely; data collection, data processing, data annotation and data publishing. It also lists software applications necessary for each step. The paper recommends that there should be a tradition of digitisation in addition to the already existing tradition of orality that is prominent in African languages and cultures.