Our system has a two-stage machine translation system. The first stage is a rule-based machine translation system, and the second stage is a normal statistical machine translation system. This idea was based on paper[3],[4],[5]. Similar studies were on paper[12],[13],[15][11]. [12] and [13] was Fresh-English translation and used SYSTRAN. [11] was Chineses-English translation for patent task and used SYSTRAN. [15] was Japanese-English translation for patent task.