Somali Extractive Text Summarization

Abstract

Somali is an Afro-asiatic language of the Cushitic family. Somali is one the most spoken languages in the Horn of Africa. It is the national language of Somalia, Official language in Ethiopia and Northern Kenya. It is also the most widely spoken language in Djibouti. Somali is also spoken by the Somalis in the diaspora. Somali is considered to be a morphologically complicated language with limited corpus and datasets. In this paper, we have scrapped paragraphs from various Somali sources and summarized the text using Extractive Text Summarization Techniques to create an extractive text summarization for Somali language.