Sciweavers

Share
EMNLP
2008

Sparse Multi-Scale Grammars for Discriminative Latent Variable Parsing

9 years 3 months ago
Sparse Multi-Scale Grammars for Discriminative Latent Variable Parsing
We present a discriminative, latent variable approach to syntactic parsing in which rules exist at multiple scales of refinement. The model is formally a latent variable CRF grammar over trees, learned by iteratively splitting grammar productions (not categories). Different regions of the grammar are refined to different degrees, yielding grammars which are three orders of magnitude smaller than the single-scale baseline and 20 times smaller than the split-and-merge grammars of Petrov et al. (2006). In addition, our discriminative approach integrally admits features beyond local tree configurations. We present a multiscale training method along with an efficient CKY-style dynamic program. On a variety of domains and languages, this method produces the best published parsing accuracies with the smallest reported grammars.
Slav Petrov, Dan Klein
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2008
Where EMNLP
Authors Slav Petrov, Dan Klein
Comments (0)
books