How Similar are Chinese and Japanese for Cross-Language Information Retrieval?

For NTCIR Workshop 5 UC Berkeley participated in the bilingual task of the CLIR track. Our focus was on Chinese topic searches against the Japanese News document collection, and on Japanese topic search against the Chinese News Document Collection. Extending our work of NTCIR 4 workshop, we performed search experiments to segment and use Chinese search topics directly as if they were Japanese topics and vice versa. We also utilized a commercial Machine Translation (MT) between the two languages, with English as a pivot language. The best performance of Chinese topic search for Japanese documents was achieved using a hybrid approach which combined MT pivot translation with direct use of Chinese topic expressions.