For improving the translation quality of transfer-based MT system,a new metric for rule evaluation was proposed and applied to rule-base optimization.At the same time,a frequency filter was used to delete redundance before new acquired rules were added into rule-base. The new optimization method was applied to a general MT system. Experimental results show that the frequency filter is helpful to provide the knowledge expansion space of MT system for new acquired rules. The translation assessment score of open test corpus(including 2500 Chinese sentences)obtained is increased by 3.58%under 5-gram Nist metric,which is two times of that obtained by previous methods.