We discuss the advantages of lexicalized tree-adjoining grammar as an alternative to lexicalized PCFG for statistical parsing, describingthe induction of a probabilistic LTAG mode...
Learning a tree substitution grammar is very challenging due to derivational ambiguity. Our recent approach used a Bayesian non-parametric model to induce good derivations from tr...
We present a novel method for inducing synchronous context free grammars (SCFGs) from a corpus of parallel string pairs. SCFGs can model equivalence between strings in terms of su...
We present a phrasal synchronous grammar model of translational equivalence. Unlike previous approaches, we do not resort to heuristics or constraints from a word-alignment model,...
Phil Blunsom, Trevor Cohn, Chris Dyer, Miles Osbor...
This paper establishes a connection between two apparently very different kinds of probabilistic models. Latent Dirichlet Allocation (LDA) models are used as "topic models&qu...