This paper presents the first dependency model for a shift-reduce CCG parser. Modelling dependencies is desirable for a number of reasons, including handling the "spurious" ambiguity of CCG; fitting well with the theory of CCG; and optimizing for structures which are evaluated at test time. We develop a novel training technique using a dependency oracle, in which all derivations are hidden. A challenge arises from the fact that the oracle needs to keep track of exponentially many gold-standard derivations, which is solved by integrating a packed parse forest with the beam-search decoder. Standard CCGBank tests show the model achieves up to 1.05 labeled F-score improvements over three existing, competitive CCG parsing models.
展开▼
