Handling organization name unknown word in Chinese-Vietnamese machine translation

Abstract

Unknown word (UKW) is an obvious problem of machine translation and named entity (NE) is the most common UKW type. In this paper, we will present a new approach based on the meaning relationship in Chinese and Vietnamese to re-translate organization name UKW. This is the most complicated NE because it consists of other NEs and entities. Applying this approach to Chinese-Vietnamese statistical machine translation (SMT), experimental results show that our approach has significantly improved machine's performance.