Amharic Text Retrieval: An Experiment Using Latent Semantic Indexing (LSI) with Singular Value Decomposition (SVD)
- Tewodros Hailemeskel Gebermariam
- Masters Thesis, School of Information Studies for…
Recently the amount of documents written in Amharic language has been dramatically increasing. Searching such content using localized and regional version of general search engine such as google.com.et returns documents containing search key terms while excluding specific characteristics of Amharic Language. In this paper, we present the design and implementation of Semantic Search Engine for Amharic documents. The search engine has Crawler, Ontology/Knowledge base, Indexer and Query Processor that consider characteristics of Amharic language. The ontology provides shared concepts Sport. This ontology is built manually by language and sport domain experts and it is used in building semantic indexer, ranker and query engine. In addition, we show how the system facilitate meaning based searching, document relevant and popularity based documents ranking.