Amharic – English Cross-lingual Information Retrieval: A Corpus Based Approach

Despite the fact that Amharic has a large number of speakers, little effort has been put in conducting researches which aim at making English documents available to the Amharic speakers. In this paper we describe the development of a corpus-based cross language information retrieval system for Amharic-English, language pairs and evaluate the system on a corpus of test documents and queries prepared for this purpose. Evaluation of the system is conducted by both monolingual and bilingual retrievals. In the monolingual run the Amharic queries are given to the system and Amharic documents are retrieved whereas in the bilingual run the the Amharic queries are given to the system after being translated into English to retrieve English documents. In addition the system is evaluated by the proportion of correct translations