... words) of Chinese Gigaword Second Edition (LDC2005T14), segmented by the Lan-guage Technology Platform (LTP)4. And for training the headword model, we use both the HIT-CDT and the HIT Chinese ... sim-plicity, efficiency and competitive accuracy. Trained on 8,975 dependency structures of a Chinese Dependency Treebank, the realizer achieves a BLEU score of 0.8874. 1 Introduction Sentence ... Input The input to our sentence realizer is a dependen-cy structure as represented in the HIT Chinese Dependency Treebank (HIT-CDT)1. In our de-pendency tree representations, dependency...