Our system has a two-stage machine translation system. The first stage is a state-of-the-art trial 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[16],[17],[18], [15] [19] and [20]. [16] and [17] was Fresh-English translation and used SYSTRAN. [15] was Chineses-English translation for patent task and used SYSTRAN. [18] [19] [20] was Japanese-English translation for patent task.