Development of an English to YorùbáMachine Translator

Abstract

The study formulated a computational model for English to Yoruba text translation process. The modelled translation process was designed, implemented and evaluated. This was with a view to addressing the challenge of English to Yoruba text machine translator. This machine translator can translate modify and non- modify simple sentences (subject verb object (SVO)). Digital resources in English and its equivalence in Yoruba were collected using the home domain terminologies and lexical corpus construction techniques. The English to Yoruba translation process was modelled using phrase structure grammar and re-write rules. The re-write rules were designed and tested using Natural Language Tool Kits (NLTKs). Parse tree and Automata theory based techniques were used to analyse the formulated model. Unified Modeling Language (UML) was used for the software design. The Python programming language and PyQt4 tools were used to implement the model. The developed machine translator was tested with simple sentences. The results for the Basic Subject-Verb-Object (BSVO) and Modified SVO (MSVO) sentences translation show that the total Experimental Subject Respondents (ESRs), machine translator and human expert average scores for word syllable, word orthography, and sentence syntax accuracies were 66.7 percent, 82.3 percent, and 100 percent, respectively. The system translation accuracies were close to a human expert.