CROSS LANGUAGE INFORMATION RETRIEVAL UNTUK BAHASA INGGRIS-JAWA DENGAN METODE BILINGUAL DICTIONARY

Abstract

Cross-language information retrieval is the process of providing queries in one language and returning relevant documents to that query which are written in other language. A popular approach to CLIR is to translate the query into the language of the documents to be retrieved. One of the simplest and most effective methods for query translation is to perform dictionary look up based a bilingual dictionary. We evaluated the effectiveness of English-Javanese CLIR system using bilingual dictionary approach. There are 500 documents were used for each language. A set of 50 queries were used in this test. First, monolingual baseline queries were created manually in English and Javanese languages. Secondly, queries in English language were automatically translated into Javanese language, and vice versa. There are two basic translation approaches : select the first translation and select all translation listed in the dictionary, for each query. The experiments were evaluated using recall and precision. The result shows that the first translation selection is suitable for both of English and Javanese document collection.

Key words

cross-language information retrieval, query translation, bilingual dictionary, English Javanese document