We explore a new Bayesian model for probabilistic grammars, a family of distributions over discrete structures that includes hidden Markov models and probabilistic context-free gr...
Tree based translation models are a compelling means of integrating linguistic information into machine translation. Syntax can inform lexical selection and reordering choices and...
Inducing a grammar from text has proven to be a notoriously challenging learning task despite decades of research. The primary reason for its difficulty is that in order to induce...
We combine the strengths of Bayesian modeling and synchronous grammar in unsupervised learning of basic translation phrase pairs. The structured space of a synchronous grammar is ...
Hao Zhang, Chris Quirk, Robert C. Moore, Daniel Gi...