Learning Tree Conditional Random Fields

Learning Tree Conditional Random Fields

Cached

Download Links

by Joseph K. Bradley , Carlos Guestrin

Citations:

BibTeX

@MISC{Bradley_learningtree,
    author = {Joseph K. Bradley and Carlos Guestrin},
    title = {Learning Tree Conditional Random Fields},
    year = {}
}

OpenURL

Abstract

We examine maximum spanning tree-based methods for learning the structure of tree Conditional Random Fields (CRFs) P (Y|X). We use edge weights which take advantage of local inputs X and thus scale to large problems. For a general class of edge weights, we give a negative learnability result. However, we demonstrate that two members of the class–local Conditional Mutual Information and Decomposable Conditional Influence– have reasonable theoretical bases and perform very well in practice. On synthetic data and a large-scale fMRI application, our methods outperform existing techniques. 1.

Keyphrases

tree conditional random field edge weight local input general class large problem synthetic data decomposable conditional influence negative learnability result reasonable theoretical base class local conditional mutual information tree-based method large-scale fmri application