Sciweavers

1324 search results - page 202 / 265
» Models for Representing Task Ontologies
Sort
View
EMNLP
2008
13 years 10 months ago
Lattice-based Minimum Error Rate Training for Statistical Machine Translation
Minimum Error Rate Training (MERT) is an effective means to estimate the feature function weights of a linear model such that an automated evaluation criterion for measuring syste...
Wolfgang Macherey, Franz Josef Och, Ignacio Thayer...
WSCG
2004
121views more  WSCG 2004»
13 years 10 months ago
User-Centric Transfer Function Specification in Augmented Reality
The quality of a 3D volume visualization heavily depends on a representative transfer function which is responsible for mapping the original density values to color and opacity. F...
Bernhard Reitinger, Christopher Zach, Alexander Bo...
SOQUA
2007
13 years 10 months ago
Faults' context matters
When choosing a testing technique, practitioners want to know which one will detect the faults that matter most to them in the programs that they plan to test. Do empirical evalua...
Jaymie Strecker, Atif M. Memon
NIPS
2003
13 years 10 months ago
Max-Margin Markov Networks
In typical classification tasks, we seek a function which assigns a label to a single object. Kernel-based approaches, such as support vector machines (SVMs), which maximize the ...
Benjamin Taskar, Carlos Guestrin, Daphne Koller
ICCV
2003
IEEE
14 years 11 months ago
Epitomic analysis of appearance and shape
See www.research.microsoft.com/jojic/epitome.htm for videos, comparisons and applications. We present novel simple appearance and shape models that we call epitomes. The epitome o...
Nebojsa Jojic, Brendan J. Frey, Anitha Kannan