Sciweavers

803 search results - page 69 / 161
» Cognates Can Improve Statistical Translation Models
Sort
View
ACL
2006
15 years 1 months ago
Minimum Risk Annealing for Training Log-Linear Models
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
David A. Smith, Jason Eisner
SIGIR
2002
ACM
14 years 11 months ago
Empirical studies in strategies for Arabic retrieval
This work evaluates a few search strategies for Arabic monolingual and cross-lingual retrieval, using the TREC Arabic corpus as the test-bed. The release by NIST in 2001 of an Ara...
Jinxi Xu, Alexander Fraser, Ralph M. Weischedel
PATMOS
2007
Springer
15 years 6 months ago
A Statistical Approach to the Timing-Yield Optimization of Pipeline Circuits
Abstract. The continuous miniaturization of semiconductor devices imposes serious threats to design robustness against process variations and environmental fluctuations. Modern ci...
Chin-Hsiung Hsu, Szu-Jui Chou, Jie-Hong Roland Jia...
WEBI
2009
Springer
15 years 6 months ago
Improving Movie Gross Prediction through News Analysis
—Traditional movie gross predictions are based on numerical and categorical movie data. But since the 1990s, text sources such as news have been proven to carry extra and meaning...
Wenbin Zhang, Steven Skiena
CAISE
2009
Springer
15 years 6 months ago
A Heuristic Method for Business Process Model Evaluation
In this paper, we present a heuristic approach for finding errors and possible improvements in business process models. First, we translate the information that is included in a m...
Volker Gruhn, Ralf Laue