Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...
We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
Background: Although there are a large number of thesauri for the biomedical domain many of them lack coverage in terms and their variant forms. Automatic thesaurus construction b...
In a semi-structured database there is no clear separation between the data and the schema, and the degree to which it is structured depends on the application. Semi-structured da...
In practice, it is quite difficult to write correct multithreaded programs due to the potential for unintended and nondeterministic interference between parallel threads. A funda...