We present a novel approach to RTE that exploits a structure-oriented sentence representation followed by a similarity function. The structural features are automatically acquired from tree skeletons that are extracted and generalized from dependency trees. Our method makes use of a limited size of training data without any external knowledge bases (eg WordNet) or handcrafted inference rules. We have achieved an accuracy of 71.1% on the RTE-3 development set performing a 10-fold cross validation and 66.9% on the RTE-3 test data.