A novel approach for cross language information retrieval

Cross-language information retrieval (CLIR) is a subfield of information retrieval dealing with retrieving information written in a language different from the language of the user´s query. The domain of CLIR is crucial in the future as vast amount of content in the web is in English. There is a need for mechanisms that can retrieve the content from English and translate it to the native language. This paper proposes a text summarization-suffix tree algorithm for the overall process of CLIR. The idea is to summarize the content and re-rank the results based on clustered coefficients. This method can improve the efficiency of the content retrieved and afford a great flexibility to the user. The key contributions of this paper are to explain the approach and discuss the key results.