Abstract
Empty categories represent an important source of information in syntactic parses annotated in the generative linguistic tradition, but empty category recovery has only started to receive serious attention until very recently, after substantial progress in statistical parsing. This paper describes a unified framework in recovering empty categories in the Chinese Treebank. Our results show that given skeletal gold standard parses, the empty categories can be detected with very high accuracy. We report very promising results for empty category recovery for automatic parses as well.