Accurate high-coverage translation is a vital component of reliable cross language information access (CLIR) systems. This is particularly true of access to archives such as Digital Libraries which are often specific to certain domains. While general machine translation (MT) has been shown to be effective for CLIR tasks in information retrieval evaluation workshops, it is not well suited to specialized tasks where domain specific translations are required. We demonstrate that effective query translation in the domain of cultural heritage (CH) can be achieved by augmenting a standard MT system with domain-specific phrase dictionaries automatically mined from the online Wikipedia. Experiments using our hybrid translation system with sample query logs from users of CH websites demonstrate a large improvement in the accuracy of domain specific phrase detection and translation.