Designing a Stemmer for Ge'ez Text Using Rule Based Approach

Ge'ez inflectional and derivational morphology of the language makes the language is very complex to stem properly. Affixations such as prefixing, infixing and suffixing are the main word formation processes in Ge¿ez language. The language is morphological very complex semantic language. This is because different words can be formed due to the wide concatenations of affixes. In the proposed techniques, affix removal and morphological analysis techniques were used. Since the Ge'ez language is morphological complex, simple stemmer algorithm that has been developed for other languages, such as English, can not effectively stem Ge'ez text. Ge¿ez is the origin of different Ethiopic languages, for example, Amharic uses a unique script which has originated from the Ge¿ez alphabet (the liturgical language of the Ethiopian Orthodox Church). Written Ge¿ez can be traced back to at least the 4th century. Ge'ez, the classical language of Ethiopia, is still used as a liturgical language by the Ethiopian Orthodox Tewahido Church (EOTC), Ethiopian Catholic Church (ECC), the Beta Israel Jewish community of Ethiopia, Germany, Eritrea and so on.