Sciweavers

205 search results - page 38 / 41
» Testing the Equivalence of Regular Languages
Sort
View
JMLR
2010
106views more  JMLR 2010»
14 years 4 months ago
Why Does Unsupervised Pre-training Help Deep Learning?
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, ...
ACL
2012
12 years 11 months ago
Crosslingual Induction of Semantic Roles
We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
Ivan Titov, Alexandre Klementiev
BMCBI
2008
175views more  BMCBI 2008»
14 years 9 months ago
Synonym set extraction from the biomedical literature by lexical pattern discovery
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...
John McCrae, Nigel Collier
ACTAC
1998
71views more  ACTAC 1998»
14 years 9 months ago
On the Information Content of Semi-Structured Databases
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...
Mark Levene
ASPLOS
2011
ACM
14 years 1 months ago
Specifying and checking semantic atomicity for multithreaded programs
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...
Jacob Burnim, George C. Necula, Koushik Sen