Discriminative Log-Linear Grammars with Latent Variables

10 years 7 months ago
Discriminative Log-Linear Grammars with Latent Variables
We demonstrate that log-linear grammars with latent variables can be practically trained using discriminative methods. Central to efficient discriminative training is a hierarchical pruning procedure which allows feature expectations to be efficiently approximated in a gradient-based procedure. We compare L1 and L2 regularization and show that L1 regularization is superior, requiring fewer iterations to converge, and yielding sparser solutions. On full-scale treebank parsing experiments, the discriminative latent models outperform both the comparable generative latent models as well as the discriminative non-latent baselines.
Slav Petrov, Dan Klein
Added 30 Oct 2010
Updated 30 Oct 2010
Type Conference
Year 2007
Where NIPS
Authors Slav Petrov, Dan Klein
Comments (0)