Sciweavers

6300 search results - page 156 / 1260
» We have it easy, but do we have it right
Sort
View
120
Voted
ACL
2008
15 years 2 months ago
Beyond Log-Linear Models: Boosted Minimum Error Rate Training for N-best Re-ranking
Current re-ranking algorithms for machine translation rely on log-linear models, which have the potential problem of underfitting the training data. We present BoostedMERT, a nove...
Kevin Duh, Katrin Kirchhoff
BILDMED
2008
119views Algorithms» more  BILDMED 2008»
15 years 2 months ago
Intuitive Mapping of Perfusion Parameters to Glyph Shape
Abstract. Perfusion data characterize the regional blood flow in human tissue. For each voxel, a time-intensity curve (TIC) represents the enhancement of a contrast agent (CA). Par...
Steffen Oeltze, Arvid Malyszczyk, Bernhard Preim
EMNLP
2008
15 years 2 months ago
Graph-based Analysis of Semantic Drift in Espresso-like Bootstrapping Algorithms
Bootstrapping has a tendency, called semantic drift, to select instances unrelated to the seed instances as the iteration proceeds. We demonstrate the semantic drift of bootstrapp...
Mamoru Komachi, Taku Kudo, Masashi Shimbo, Yuji Ma...
MODELLIERUNG
2008
15 years 2 months ago
Domain-Specific Languages for Wireless Sensor Networks
The development of software for wireless sensor networks is involved and complex. This does not only impose much work on programmers but also prevents domain experts from directly ...
Daniel A. Sadilek
ACSW
2006
15 years 2 months ago
Description of bad-signatures for network intrusion detection
Today, a computer network is under constant assault from attacks. In Computer Science, NIDS are used in order to protect a computer network against these intrusions. These systems...
Michael Hilker, Christoph Schommer