Exploring the Treatment of Selected Typological Characteristics of Tswana in LFG

Ansu Berg, Rigardt Pretorius and Laurette Pretorius

Abstract

Tswana is a Bantu language in the south eastern zone of Bantu languages and one of the eleven official languages of South Africa. From a linguistic as well as a computational point of view the language is a lesser-studied and under-resourced language. Recently a project was undertaken to describe the syntactic structure of Tswana in the LFG formalism (Dalrymple, 2001). This project is expanded by applying the syntactic structure of Tswana in the Xerox Language Environment (XLE) parser toolkit (Xerox Palo Alto Research Centre, 2007). In this paper a short overview of selected distinctive typological characteristics of Tswana, including the word order, agglutinative character, disjunctive orthography and agreement, is presented. The aim is to demonstrate how selected instances of agreement in Tswana can be treated in LFG and XLE.

Link to pdf of paper