Incremental Bayesian Networks for Natural Language Parsing

Channel:

Google TechTalks

Subscribers:

349,000

Published on October 9, 2007 3:12:02 AM ● Video Link: https://www.youtube.com/watch?v=ai1QZGuIC6A

Duration: 1:00:59

6,716 views

17

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...