Sciweavers

8099 search results - page 361 / 1620
» Higher-Order Task Models
Sort
View
COLING
2010
15 years 1 months ago
Local lexical adaptation in Machine Translation through triangulation: SMT helping SMT
We present a framework where auxiliary MT systems are used to provide lexical predictions to a main SMT system. In this work, predictions are obtained by means of pivoting via aux...
Josep Maria Crego, Aurélien Max, Fran&ccedi...
196
Voted
COLING
2010
15 years 1 months ago
Discriminant Ranking for Efficient Treebanking
Treebank annotation is a labor-intensive and time-consuming task. In this paper, we show that a simple statistical ranking model can significantly improve treebanking efficiency b...
Yi Zhang 0003, Valia Kordoni
ICASSP
2011
IEEE
14 years 10 months ago
Unsupervised vocabulary discovery using non-negative matrix factorization with graph regularization
In this paper, we present a model for unsupervised pattern discovery using non-negative matrix factorization (NMF) with graph regularization. Though the regularization can be appl...
Meng Sun, Hugo Van hamme
ICASSP
2011
IEEE
14 years 10 months ago
Automatic speech recognition using Hidden Conditional Neural Fields
Hidden Conditional Random Fields(HCRF) is a very promising approach to model speech. However, because HCRF computes the score of a hypothesis by summing up linearly weighted featu...
Yasuhisa Fujii, Kazumasa Yamamoto, Seiichi Nakagaw...
SDM
2012
SIAM
252views Data Mining» more  SDM 2012»
13 years 9 months ago
Learning from Heterogeneous Sources via Gradient Boosting Consensus
Multiple data sources containing different types of features may be available for a given task. For instance, users’ profiles can be used to build recommendation systems. In a...
Xiaoxiao Shi, Jean-François Paiement, David...