Report on CLIR Task for the NTCIR-4 Evaluation Campaign

This paper describes our second participation in an evaluation campaign involving the Chinese, Japanese, Korean and English languages (NTCIR-5). Our participation is motivated by four objectives: 1) study the retrieval performances of various IR models for these languages; 2) compare the relative retrieval effectiveness of bigram and automatic wordsegmenting approaches for Chinese and Japanese languages; 3) propose a new blind-query expansion hopefully capable of improving mean average precision; and 4) evaluate the relative performance of the various merging strategies used to combine separate result lists extracted from a corpus written in English, Chinese, Japanese or Korean.