Deep belief networks are a powerful way to model complex probability distributions. However, it is difficult to learn the structure of a belief network, particularly one with hidd...
Ryan Prescott Adams, Hanna M. Wallach, Zoubin Ghah...
Clustering using the Hilbert Schmidt independence criterion (CLUHSIC) is a recent clustering algorithm that maximizes the dependence between cluster labels and data observations ac...
Wenliang Zhong, Weike Pan, James T. Kwok, Ivor W. ...
We consider the problem of learning Gaussian multiresolution (MR) models in which data are only available at the finest scale and the coarser, hidden variables serve both to captu...
Myung Jin Choi, Venkat Chandrasekaran, Alan S. Wil...
This paper presents a novel sequence labeling model based on the latent-variable semiMarkov conditional random fields for jointly extracting argument roles of events from texts. ...
We propose new data structures for navigation in sequences of balanced parentheses, a standard tool for representing compressed trees. The most striking property of our approach is...