Outomatiese lemma-identifisering en die dilemma met die lemma in Setswana

Abstract

Projects in human language technologies do not only imply challenges for programmers but also for grammarians. In a recent project to develop an automatic lemmatiser for Setswana, the problem arose as to what the lemma in Setswana should be, as no clearcut definition exists in the Bantu language grammars or lexicographic studies. This article aims to determine and discuss the term “lemma” in Setswana as it should be applied in automatic lemmatisation.