Information Extraction Model for Afan Oromo News Text

The Oromoo writing system is a modification to Latin writing system. Thus, the language shares a lot of features with English writing with some modification. The writing system of the language is known as ¿qubee Afaan Oromoö is straightforward which is designed based on the Latin script. Thus letters in English language are also in Oromoo except the way it is written. AOTIE have training and testing phases. During training phase, the classifier model is generated based on the extracted NP chunks from tagged training data. The generated classifier model is used for predicting the category of the candidate texts during the testing phase. The output of the information extraction subcomponent is the candidate texts with their respective predicted category, which is used as an input to the post processing component.