We apply Combinatory Categorial Grammar to wide-coverage parsing in Chinese with the new Chinese CCGbank, bringing a formalism capable of transparently recovering non-local dependencies to a language in which they are particularly frequent.
We train two state-of-the-art English CCG parsers: the parser of Petrov and Klein (P&K), and the Clark and Curran (C&C) parser, uncovering a surprising performance gap between them not observed in English -- 72.73 (P&K) and 67.09 (C&C) F-score on PCTB 6.
We explore the challenges of Chinese CCG parsing through three novel ideas: developing corpus variants rather than treating the corpus as fixed; controlling noun/verb and other POS ambiguities; and quantifying the impact of constructions like pro-drop.