We show that the automatically induced latent variable grammars of Petrov et al. (2006) vary widely in their underlying representations, depending on their EM initialization point...
This paper presents a grammar formalism in which constituent graphs are unions of a continuous surface tree and a discontinuous deep tree. The formalism has an object-oriented desi...
We present three approaches for unsupervised grammar induction that are sensitive to data complexity and apply them to Klein and Manning's Dependency Model with Valence. The ...
Valentin I. Spitkovsky, Hiyan Alshawi, Daniel Jura...
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...
Dependency parsers show syntactic relations between words using a directed graph, but comparing dependency parsers is difficult because of differences in theoretical models. We de...