This paper presents several modifications of the standard annotation projection algorithm for syntactic structures in crosslingual dependency parsing.Our approach reduces projection noise and includes efficient data sub-set selection techniques that have a substantial impact on parser performance in terms of labeled attachment scores.We test our techniques on data from the Universal Dependency Treebank and demonstrate the improvements on a number of language pairs.We also look at treebank translation including syntaxbased models and data combination techniques that push the performance even further.We achieve absolute improvements of up to over seven points in labeled attachment scores pushing the state-of-the art in cross-lingual dependency parsing for all language pairs tested in our experiments.