Information Extraction (IE) aims to automatically generate a large knowledge base from natural language text, but progress remains slow. Supervised learning requires copious human annotation, while unsupervised and weakly supervised approaches do not deliver competitive accuracy. As a result, most fielded applications of IE, as well as the leading TAC-KBP systems, rely on significant amounts of...

Stefan Treue be adequately processed. A well-studied example of such a selection process is selective attention, the ability Cognitive Neuroscience Laboratory Sektion fü r Visuelle Sensomotorik to allocate processing resources in a nonhomogeneous manner, enabling the detailed analysis of stimuli of inter-Dept. of Neurology University of Tü bingen est while at the same time not wasting neural pr...

Although many variants of stochastic gradient descent have been proposed for large-scale convex optimization, most of them require projecting the solution at each iteration to ensure that the obtained solution stays within the feasible domain. For complex domains (e.g., positive semidefinite cone), the projection step can be computationally expensive, making stochastic gradient descent unattrac...