This paper presents a novel semisupervised learning algorithm called Active Deep Networks (ADN), to address the semi-supervised sentiment classification problem with active learni...
Unsupervised learning algorithms aim to discover the structure hidden in the data, and to learn representations that are more suitable as input to a supervised machine than the ra...
This paper shows that semantic role labeling is a consequence of accurate verbal predicate labeling. In doing so, the paper presents a novel type of semantic feature for verbal pr...
Hansen A. Schwartz, Fernando Gomez, Christopher Mi...
Occam’s razor is the principle that, given two hypotheses consistent with the observed data, the simpler one should be preferred. Many machine learning algorithms follow this pr...
This paper describes the development and evaluation of Synote, a freely available accessible web based application that makes multimedia web resources (e.g. podcasts) easier to ac...