Patent MT is emerging as a killer application domain for MT, as there is a strong need for fast and cheap translations for patent documents. Most of the Korean-English MT engines hitherto have suffered from the poor syntactic analysis performance and the lack of linguistic resources. We customized a Korean syntactic parser based on the linguistic characteristics of the patent documents, especially focusing on minimizing the noise in acquiring the co-occurrence data for Korean syntactic parsing. We will show that the improvement of the quality of co-occurrence data and other customization processes can lead to the im prove ment of the parsing accuracy and thus the improvement of the translation quality.