An investigation into lemmatization in Southern Sotho

• Main Author: Makgabutlane, Kelebohile Hilda
• Other Authors: Kosch, I. M.
• Format: Others
• Published: 2015
• Subjects: 413.028; Lexicography > Data processing; Sotho language > Lexicography; Lemmatization
• Online Access: http://hdl.handle.net/10500/17302

Lemmatization refers to the process whereby a lexicographer assigns a specific place in a dictionary to a word which he regards as the most basic form amongst other related forms. The fact that in Bantu languages formative elements can be added to one another in an often seemingly interminable series till quite long words are produced, evokes curiosity as far as lemmatization is concerned. Being aware of the productive nature of Southern Sotho it is interesting to observe how lexicographers go about handling the question of morphological complexities they are normally faced with in the process of arranging lexical items. This study has shown that some difficulties are encountered as far as adhering to the traditional method of alphabetization is concerned. It does not aim at proposing solutions but does point out some considerations which should be borne in mind in the process of lemmatization. === African Languages === M.A. (African Languages)