Chinese and Korean Topic Search of Japanese News Collections

UC Berkeley participated in the pivot bilingual task of the CLIR track at NTCIR Workshop 4. Our focus was on Chinese and Korean searches against the Japanese News document collection, using English as a pivot language. For comparison of our pivot techniques, we submitted Japanese monolingual and English Japanese bilingual search rankings as well. Two different commercial translation software packages were used in quite different ways – one did standard query translation from Chinese or Korean topics to English and then to Japanese, while the other was used to translate the Japanese corpus to English wordby-word using ‘fast document translation’. Another interesting search approach was to segment and use Chinese search topics directly as if they were Japanese topics