Sciweavers

Share
4 search results - page 1 / 1
» Combining Unsupervised and Supervised Alignments for MT: An ...
Sort
View
EMNLP
2010
10 years 9 months ago
Combining Unsupervised and Supervised Alignments for MT: An Empirical Study
Word alignment plays a central role in statistical MT (SMT) since almost all SMT systems extract translation rules from word aligned parallel training data. While most SMT systems...
Jinxi Xu, Antti-Veikko I. Rosti
INTERSPEECH
2010
10 years 6 months ago
Combining many alignments for speech to speech translation
Alignment combination (symmetrization) has been shown to be useful for improving Machine Translation (MT) models. Most existing alignment combination techniques are based on heuri...
Sameer Maskey, Steven J. Rennie, Bowen Zhou
ICAI
2004
11 years 1 months ago
A Comparison of Resampling Methods for Clustering Ensembles
-- Combination of multiple clusterings is an important task in the area of unsupervised learning. Inspired by the success of supervised bagging algorithms, we propose a resampling ...
Behrouz Minaei-Bidgoli, Alexander P. Topchy, Willi...
NECO
2011
10 years 6 months ago
Least Squares Estimation Without Priors or Supervision
Selection of an optimal estimator typically relies on either supervised training samples (pairs of measurements and their associated true values), or a prior probability model for...
Martin Raphan, Eero P. Simoncelli
books