Classifiers for data-driven deep sentence generation (original) (raw)

State-of-the-art statistical sentence generators deal with isomorphic structures only. Therefore, given that semantic and syntactic structures tend to differ in their topology and number of nodes, i.e., are not isomorphic, statistical generation saw so far itself confined to shallow, syntactic generation. In this paper, we present a series of fine-grained classifiers that are essential for data-driven deep sentence generation in that they handle the problem of the projection of non-isomorphic structures.