We describe an efficient semantic service discovery scheme called UbiSearch for a large-scale ubiquitous computing environment. We propose a semantic service discovery network on the semantic vector space where semantically adjacent services are mapped into nearby positions so that the similar services are registered in a cluster of resolvers. Using this mapping technique, the search space for a query is efficiently confined within a minimized cluster region while keeping a high accuracy. We also propose techniques to evenly distribute service indexes to the resolvers and reduce the number of resolvers to visit. Our simulation study shows that UbiSearch provides good semantic searchability comparable to centralized indexing system. At the same time, it supports scalable semantic queries with low communication overhead, balanced load distribution among resolvers for service registration and query processing, and personalized semantic matching.