Sciweavers

51 search results - page 8 / 11
» Measure Word Generation for English-Chinese SMT Systems
Sort
View
NLE
2007
180views more  NLE 2007»
14 years 9 months ago
Segmentation and alignment of parallel text for statistical machine translation
We address the problem of extracting bilingual chunk pairs from parallel text to create training sets for statistical machine translation. We formulate the problem in terms of a s...
Yonggang Deng, Shankar Kumar, William Byrne
EOR
2008
106views more  EOR 2008»
14 years 9 months ago
Analysis of a discrete-time preemptive resume priority buffer
In this paper, we analyze a discrete-time preemptive resume priority queue. We consider two classes of customers which have to be served, where customers of one class have preempt...
Joris Walraevens, Bart Steyaert, Herwig Bruneel
JMLR
2012
13 years 2 days ago
Bounding the Probability of Error for High Precision Optical Character Recognition
We consider a model for which it is important, early in processing, to estimate some variables with high precision, but perhaps at relatively low recall. If some variables can be ...
Gary B. Huang, Andrew Kae, Carl Doersch, Erik G. L...
CSL
1999
Springer
14 years 9 months ago
A hidden Markov-model-based trainable speech synthesizer
This paper presents a new approach to speech synthesis in which a set of cross-word decision-tree state-clustered context-dependent hidden Markov models are used to define a set o...
R. E. Donovan, Philip C. Woodland
HICSS
2003
IEEE
117views Biometrics» more  HICSS 2003»
15 years 2 months ago
Performance of Integrated Supply Chains - An International Case Study in High Tech Manufacturing
The aim of this study is to identify factors that improve the performance of integrated supply chains (SCs). We developed the ‘extended strategic alignment model’ based on the ...
David C. L. Kuo, Martin Smits