We explore the near-synonym lexical choice problem using a novel representation of near-synonyms and their contexts in the latent semantic space. In contrast to traditional latent...
The FastInf C++ library is designed to perform memory and time efficient approximate inference in large-scale discrete undirected graphical models. The focus of the library is pro...
Ariel Jaimovich, Ofer Meshi, Ian McGraw, Gal Elida...
This paper considers application of Deep Belief Nets (DBNs) to natural language call routing. DBNs have been successfully applied to a number of tasks, including image, audio and ...
Ruhi Sarikaya, Geoffrey E. Hinton, Bhuvana Ramabha...
Motivated by the observation that coarse and fine resolutions of an image reveal different structures in the underlying visual phenomenon, we present a model based on the Deep B...
We present an approach to synthesizing shapes from complex domains, by identifying new plausible combinations of components from existing shapes. Our primary contribution is a new...