Afan Oromo News Text Summarizer

Abstract

Information overload is a global problem that requires solution. Automatic text summarizer, a computer program that summarizes a text, is one of the natural language processing technologies that have got researchers focus to help information users. In this study, three methods have been used for the development of Afan Oromo news text summarizers and the resulting three summarizers have been evaluated both objectively and subjectively. These are : S1 that uses term frequency and position methods without Afan Oromo stemmer and language specific lexicons (synonyms and abbreviations); S2 is a summarizer with combination of term frequency and position methods with Afan Oromo stemmer and language specific lexicons and S3 is with improved position method and term frequency as well as the stemmer and language specific lexicons . The result of objective evaluation shows that S3 outperformed the two summarizers (S1 and S2) by 47% and 34 %. Moreover, the subjective evaluation result also shows that S3 better than the other summarizers (S1 and S2) with informativeness, linguistic quality, and coherence and structure. Keywords