Chasing the ghost: recovering empty categories in the Chinese Treebank

摘要

Empty categories represent an impor-tant source of information in syntactic parses annotated in the generative linguis-tic tradition, but empty category recovery has only started to receive serious atten-tion until very recently, after substantial progress in statistical parsing. This paper describes a unified framework in recover-ing empty categories in the Chinese Tree-bank. Our results show that given skele-tal gold standard parses, the empty cate-gories can be detected with very high ac-curacy. We report very promising results for empty category recovery for automatic parses as well.