Cross-Lingual Information Retrieval: A Dictionary-Based Query Translation Approach

Abstract

The rapidly increasing demographics of the Internet population and the abundance of multilingual content on the web increased the communication in multiple languages. Most of the people use their regional languages to express their need and the language diversity becomes a great barrier. Cross-Lingual Information Retrieval (CLIR) provides a solution for that language barrier which allows a user to ask a query in the native language and get the relevant documents in the different language. In this paper we build a dictionary-based query translation system. Queries are tokenized and multi-words query terms are created using N-gram technique. Out of vocabulary (OOV) terms are transliterated using the proposed OOVTTM technique. Target documents are retrieved using vector space retrieval model. Experiment results represent that the proposed approach achieves better results.