The Use of a Hybrid Machine Translation System in China´s Government Portals

This paper introduces a hybrid machine translation system which can be used to translate natural languages´ sentences in government portals by exploiting both a translation memory and a statistical-based translation model. Our study shows that an automatically derived translation memory can be used within a statistical framework to often find translations of higher probability than those which use solely a statistical model. This hybrid Machine Translation system can be used in China´s government portals to help overcome the language barrier which causes the non-Chinese speakers the limited sharing of information and the low accessibility to the services.