Incremental Bayesian Networks for Natural Language Parsing

Back


Google Tech Talks
August 13, 2007

ABSTRACT

Natural language parsing is a particularly challenging structure prediction problem, due to the large space of output structures and the complex nature of the statistical dependencies between features of the output structures. Typically these statistical dependencies are specified by hand, but recently there has been interest in using latent variables to induce them automatically. In this talk I will present a framework for structure prediction with latent variables based on a form of Dynamic Bayesian Network called Incremental Sigmoid Belief Networks (ISBNs), and illustrate how it can be applied to parsing. Approximations to ISBNs have achieved...

Channel: Howto & Style
Uploaded: October 8, 2007 at 9:06 pm
Author: googletechtalks

Length: 01:00:58
Rating: 3.40
Views: 1911

Tags: google howto incremental bayesian networks

Embed Code: Paste this code in your page


Video Comments:
xRen0x (September 6, 2008 at 3:43 pm)
his name is on the first frame of this video
pranavaswaroop (July 16, 2008 at 3:48 pm)
Very interesting, may I know who the speaker is?