Discriminative Reranking for Natural Language Parsing.
Discriminative Reranking for Natural Language Parsing Michael Collins and Terry Koo Massachusetts Institute of Technology This paper considers approaches which rerank the output of an existing probabilistic parser. The base parser produces a set of candidate parses for each input sentence, with associated probabilities that de ne an initial ranking of these parses. A second model then attempts to improve upon this initial ranking, using additional features of the tree as evidence. The strength