The Application of the Comparable Corpora in Chinese-English Cross-Lingual Information Retrieval

This paper proposes a novelChinese-English Cross-Lingual Information Retrieval (CECLIR) model PME,in which bilingual dictionary and comparable corpora are used totranslate the query terms. The proximity and mutual information of theterm-pairs in the Chinese and English comparable corpora are employednot only to resolve the translation ambiguities but also to perform thequery expansion so as to deal with the out-of-vocabulary issues in theCECLIR. The evaluation results show that the query precision of PMEalgorithm is about 84.4% of the monolingual information retrieval.