Sciweavers

Share
ACL
2007

Constituent Parsing with Incremental Sigmoid Belief Networks

9 years 1 months ago
Constituent Parsing with Incremental Sigmoid Belief Networks
We introduce a framework for syntactic parsing with latent variables based on a form of dynamic Sigmoid Belief Networks called Incremental Sigmoid Belief Networks. We demonstrate that a previous feed-forward neural network parsing model can be viewed as a coarse approximation to inference with this class of graphical model. By constructing a more accurate but still tractable approximation, we significantly improve parsing accuracy, suggesting that ISBNs provide a good idealization for parsing. This generative model of parsing achieves state-of-theart results on WSJ text and 8% error reduction over the baseline neural network parser.
Ivan Titov, James Henderson
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2007
Where ACL
Authors Ivan Titov, James Henderson
Comments (0)
books