Evaluating the Bantu parametric grammar in grammatical framework using Swahili grammar

Abstract

Monologue grammar development for under-resourced languages is very slow and laborious (involves creating rules to generate the computational grammar to enable analysis and synthesis of the language(s) in question). However, the need for computational grammar continues to soar in this technology-driven economy for information synthesis and analysis. This paper aims to set up an experiment in the grammatical framework (GF), to evaluate the efficiency and effectiveness of the Bantu parameterized grammar to bootstrap a new grammar for Swahili. The goal is to investigate how this approach of bootstrapping grammar in a multilingual environment is effective and efficient in reducing the development effort. The bootstrapping approach uses the GF morphology-driven approach to develop portable and unique segments of Swahili grammar. The bootstrapped Swahili grammar resulted in a shareability of 100%, 71.11%, 68.75%, and 91.41% at category linearization, paradigms, parameters and syntax rules respectively. The portability was at 15.55%, 18.57%, and 8.59% at paradigms, parameters and syntax rules, respectively. Finally, this paper contributes in: first, provides an approach that leads to an effective and efficient method for developing and bootstrapping computational grammar for the under-resourced Bantu languages. Secondly, the research provided a Swahili grammar.