Computational morphological analysis of Yorùbá language words

Abstract

Nigeria official languages are English, Yorùbá, Igbo and Hausa. The focus of the study reported in this paper is to develop learning tool that can assist learners to learn the Yorùbá language using its alphabets. The study is critical to Yorùbá language, because of its endangerment. There is need to introduce different learning tools that can mitigate its extinction. A Yorùbá word perfect system was developed to assist people in learning the Yorùbá language. English and Yorùbá words formation are experimented using computational morphological approach (word formation). The theoretical framework considered Finite state automata (FSA) to realise different ways of combining the consonants and vowels to form word. Two to five letter words were considered. The system was designed and implemented using UML tools and python programming language.The system will teach the users on how the words are formed, and the number of syllables in each word. The user need not to know how to tone mark word before he/she can use the system. Any word typed will be analysed according to its number of syllables. This approach produces representatives of all parts of speech (POS) of the two languages. It produces corpora for the two languages.