Afaan Oromo-Arabic Cross Language Information Retrieval.

Abstract

The objective of Cross Language Information Retrieval (CLIR) system is to put forward users with access to information that is in different language from their queries. It has the ability to issue a query in one language and retrieve documents in another language. In multi-lingual country like Ethiopia it is common to see language barriers while seeking information in language other than ones mother tongue. Afaan Oromo is one of the major languages that are widely spoken and used in Ethiopia. In spite of the fact that, Afaan Oromo has a large number of speakers little effort has been put in conducting research which aim at making Arabic documents available to Afaan Oromo speakers. Afaan Oromo speakers want to speak Arabic because of many fundamental facts. Among them are the diplomatic relation and the issue of public diplomacy is playing crucial role in the lives nations. This study is endeavor to develop Afaan Oromo-Arabic CLIR system which enables Afaan Oromo native speakers to access and retrieve the huge online information source that are available in Arabic by writing queries using their own language. The approach selected and followed in this study is dictionary-based CLIR system. For this study a lot of documents like Qur‟aana chapters, Bible chapters and other religious documents are included. The system is tested with 20 queries and 40 documents. Experiments were conducted by using one possible translation to Afaan Oromo query terms into Arabic. The retrieval effectiveness of the system is measured using recall and precision for both monolingual and bilingual runs. The experiment returned a Maximum Average Precision of 0.706 and 0.675 for monolingual Afaan Oromo queries and also 0.617 and 0.7 bilingual translated Arabic queries runs respectively. From these outcomes, it can be concluded that, the performance of their trivial system could be increased with use of larger and clean corpora and by using different methods of like automatic alignment of words for translation.