Alert icon
We're changing our privacy policy. This stuff matters.  Learn more  Dismiss

Incremental Bayesian Networks for Natural Language Parsing

Loading...

Sign in or sign up now!
5,100
Loading...
Alert icon
Sign in or sign up now!
Alert icon

Uploaded by on Oct 8, 2007

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...

Category:

Howto & Style

Tags:

License:

Standard YouTube License

  • likes, 2 dislikes

Link to this comment:

Share to:
see all

All Comments (4)

Sign In or Sign Up now to post a comment!
  • Awesome topic; too bad this lecturer is dry as....

  • @pranavaswaroop  James B. Henderson

  • his name is on the first frame of this video

  • Very interesting, may I know who the speaker is?

Loading...

0 / 00Unsaved Playlist Return to active list
    1. Your queue is empty. Add videos to your queue using this button:
      or sign in to load a different list.
    Loading...Loading...Saving...
    • Clear all videos from this list
    • Learn more