EMNLP
2008
14 years 1 months ago
2008
This paper investigates two strategies for improving coreference resolution: (1) training separate models that specialize in particular types of mentions (e.g., pronouns versus pr...
CC
2001
Springer
14 years 4 months ago
2001
Springer
Compilers can exploit knowledge that a variable has a fixed known value at a program point for optimizations such as code specialization and constant folding. Recent work has shown...
CCGRID
2006
IEEE
14 years 4 months ago
2006
IEEE
MPICH2 provides a layered architecture for implementing MPI-2. In this paper, we provide a new design for implementing MPI-2 over InfiniBand by extending the MPICH2 ADI3 layer. Ou...
ICMCS
2005
IEEE
14 years 6 months ago
2005
IEEE
Cross-Layer Design (CLD) is a new paradigm for network architecture that allows us to make better use of network resources by optimizing across the boundaries of traditional netwo...
IPPS
2006
IEEE
14 years 6 months ago
2006
IEEE
Traditional code optimizers have produced significant performance improvements over the past forty years. While promising avenues of research still exist, traditional static and p...
EWSN
2008
Springer
15 years 23 hour ago
2008
Springer
Storing and disseminating coded information instead of the original data can bring significant performance improvements to sensor network protocols. Such methods reduce the risk of...
CADE
2006
Springer
15 years 22 days ago
2006
Springer
In this paper, we discuss a lightweight approach to eliminate the overhead due to implicit type arguments during higher-order unification of dependently-typed terms. First, we show...
CADE
2007
Springer
15 years 22 days ago
2007
Springer
We present a novel reasoning calculus for Description Logics (DLs)--knowledge representation formalisms with applications in areas such as the Semantic Web. In order to reduce the ...
ICPR
2004
IEEE
15 years 1 months ago
2004
IEEE
Recent empirical work has shown that combining predictors can lead to significant reduction in generalization error. The individual predictors (weak learners) can be very simple, ...
103
click to vote
ICDE
2003
IEEE
15 years 1 months ago
2003
IEEE
The output of boolean association rule mining algorithms is often too large for manual examination. For dense datasets, it is often impractical to even generate all frequent items...