We give the first polynomial time prediction strategy for any PAC-learnable class C that probabilistically predicts the target with mistake probability poly(log(t)) t = ˜O 1 t w...
We introduce a probabilistic formalism subsuming Markov random fields of bounded tree width and probabilistic context free grammars. Our models are based on a representation of Bo...
David A. McAllester, Michael Collins, Fernando Per...
Today there is a relatively large body of work on automatic acquisition of lexicosyntactical preferences (subcategorization) from corpora. Various techniques have been developed t...
Current tree-to-tree models suffer from parsing errors as they usually use only 1best parses for rule extraction and decoding. We instead propose a forest-based tree-to-tree model...
This paper addresses the problem of learning to map sentences to logical form, given training data consisting of natural language sentences paired with logical representations of ...
Tom Kwiatkowksi, Luke S. Zettlemoyer, Sharon Goldw...