English to Yorùbá Machine Translation System using Rule-Based Approach

Rule-based approach is a good approach for Machine Translation System used for language with lots of grammar which Yorùbá language is one. In this paper we present Rule-based approach to Yorúbà Machine Translation System. The popularity of Yorúbà language among the three main languages in Nigeria calls for the need to computerise the language. Transfer Rule-Based Machine Translation is use in the development of the System. It was used because it allows us to use manual tagging of the part of speech (POS). Rewrite rules was developed for the two languages (Yorùbá and English). The data was collected from home domain vocabularies. The re-write rule was verified using Natural Language Toolkits (NLTKs) and implement using python programming language. The system interface gives the user the opportunity to type simple English language sentence and the resulting Yorùbá Translation is displayed. The result shows that the system performance is close to the expert opinion, having considered the scope for which the system is developed. Based on the result gathered there are some issues to address that could be considered in a future work. Keywords—Machine translation, Yorùbá language, rule-based approach, English language, sentence