Open source spellchecker for Luhy a-Lulogoli

Abstract

This report provides a brief overview of spell checking software and describes the process of constructing a spell checker for the Lulogoli language and its implementation for the Hunspell spell checker engine. The word list is an adaptation of word roots coming from the Hymn books, story books and spoken language. Recognition of morphologically complex words, which are common in Lulogoli due to its agglutinative nature, is made possible by the affix file which has been built based on ready made morpheme segmentation of word derivations appearing in the corpus. Rules derived in the latter process have been improved by semantic classification of all involved roots, for which a system has been created based on corpus analysis in combination with knowledge on the capability of each affix to accept roots from different semantic classes. The developed spellchecker for Lulogoli language using Hunspell language tools is composed of 13,943 root words and more than 600 affix rules that are used to generate words in the order of more than 100,000 Lulogoli words. Results obtained in applying the developed spellchecker in OpenOffice Writer have shown a fairly acceptable performance that has practical use in spell checking documents in the Lulogoli but can be used with high acceptability for Lutiriki, Lunyole, Lukisa, Luwanga, Luisukha and luidakho. We also propose the use of this tool for correction and collation of more language corpus for Lulogoli thus bridging the digital divide between Lulogoli and other developed languages. The resulting spellchecker is a working proof of concept, to be further improved and integrated in the Free open source software.