Workshop: Somali Corpus: state of the art tool for linguistic analysis – November 2015
Speaker: Jama Musse Jama, Oriental University of Naples, Italy
Organizer: Centro Studi Somali, Roma
The main aim of the presented research consists of building an electronic corpus of the Somali language, which is syntactically annotated and verified from the linguistic point of view, and to make it available for researchers by providing it with several applications for search and retrieval, and the linguistic analysis of the Somali texts.
Furthermore, the research focuses on the theoretical study, and the practical implementation, of several IT applications for the study and analysis of Somali texts. These include concordance generating tools, a semi-automatic morphological tagger, spelling checker and “word behaviour” (WB) generating tool (a Natural Language Process (NLP) tool to analyse the word in its discourse context).
For further details on somali Corpus, please visit Kaydka Af Soomaaliga.