Mostly the computer based information retrieval systems focus on texts in the English language. But it is the need of the hour that these information systems should be developed in other language’s as well. With the advent of the internet and the World Wide Web, systems supporting multiple languages are much needed.
Every language has its own characteristics which should be mould in an information system. The characteristics of every language, such as syntactic and semantic structure, usage of grammar and content oriented words, formation of sentences and other characteristics are different. As a result, the direct adaptation of classical information retrieval techniques is possible for some languages, whereas for others it is not possible. Languages, such as Turkish, require a detailed analysis before stemming as it is an agglutinative language.
Every language has its own characteristics and the retrieval systems must be adapted to handle the use and complexity of the language. The multi-lingual information retrieval systems enable queries in one language to retrieve documents in other languages. The effectiveness of a multilingual retrieval system sometimes depends on the intended body of users. Very often the users did not know the other language so that they get benefited from a multi-lingual system.