Abstract      

Ontological annotation, a machine-readable and explicit description of shared concepts in a domain of discourse has always been employed in European languages to aid computer in Natural Language Processing (NLP). This method, however, has not been so much employed in African languages including the Yorùbá language. This paper, therefore, proposes ontological annotation as a way to prepare the implicit knowledge of Yorùbá core grammar for (NLP) activities by isolating and tagging some Yorùbá nouns into their component features, such that the model implemented is both human and machine readable. Relational Content Analysis (RCA) as a method of ontological annotations was adopted to design a conceptual sample model for selected Yorùbá nouns. The informally perceived domain knowledge of Yorùbá nouns were extracted randomly, using intermediate representations based on tabular and entity-relation notations. Protégé 4.5, a semantic web editing tool was used to implement a sample model for Yorùbá nouns according to Bamgbose (1990)’s “Fonó̩ló̩jì àti Gírámà Yorùbá”. The model named YORNOB (Yorùbá Noun Ontology according to Bamgbose), at the final edge, provides the semantic load and properties of each of the nouns in it. The definitions in the annotation serve as backbones for machine learning, web searching and artificial intelligence agents and other (NLP) systems. The model developed in this paper serve as repositories of data and shared terminology for Yorùbá language development and use. This paper recommends that more on ontological annotations for Yorùbá grammar concepts are needed to foster Yorùbá language engineering.