EXPLORE PUBLICATIONS BY COUNTRIES

Afan Oromo stemmer, Rule based Stemmer, context sensitive stemming

Most natural language processing systems use stemmer as a separate module in their architecture. Specially, it is very significant for developing, machine translator, speech recognizer and search engines. In this thesis work, a stemming system for Afan Oromo is presented. This system takes as input a word and removes its affixes according to a rule based algorithm. The result of the study is a prototype context sensitive iterative stemmer for Afan Oromo. Error counting technique was employed to evaluate the performance of this stemmer. The errors were analyzed and classified into two different categories: under stemming and over stemming errors. For testing purpose corpus which is collected from different public Afaan Oromo newspapers and bulletins is used. Newspapers, bulletins and public magazines are considered as consisting different issues of the community: social, economical, technological and political issues. This will reduce the probability of making the corpus biased toward some specific words that do not appear in everyday life. to make the testing set balanced. According to the evaluation of the experiments, it can be concluded that an overall accuracy of the stemmer is encouraging which shows stemming can be performed with low error rates in high inflected languages such as Afan Oromo.