Sciweavers

384 search results - page 8 / 77
» Get another label
Sort
View
ICASSP
2009
IEEE
14 years 1 months ago
Unsupervised acoustic and language model training with small amounts of labelled data
We measure the effects of a weak language model, estimated from as little as 100k words of text, on unsupervised acoustic model training and then explore the best method of using ...
Scott Novotney, Richard M. Schwartz, Jeff Ma
DASFAA
2005
IEEE
134views Database» more  DASFAA 2005»
14 years 10 days ago
An Improved Prefix Labeling Scheme: A Binary String Approach for Dynamic Ordered XML
A number of labeling schemes have been designed to facilitate the query of XML, based on which the ancestor-descendant relationship between any two nodes can be determined quickly....
Changqing Li, Tok Wang Ling
INFOCOM
2000
IEEE
13 years 11 months ago
Trainet: A New Label Switching Scheme
— Trainet, a new scheme to extend MPLS (Multi Protocol Label Switching) is presented. The scheme works much like the subway system in a large metropolitan area. Each (unidirectio...
Yehuda Afek, Anat Bremler-Barr
ASUNAM
2010
IEEE
13 years 8 months ago
Semi-Supervised Classification of Network Data Using Very Few Labels
The goal of semi-supervised learning (SSL) methods is to reduce the amount of labeled training data required by learning from both labeled and unlabeled instances. Macskassy and Pr...
Frank Lin, William W. Cohen
LICS
2003
IEEE
13 years 12 months ago
Labelled Markov Processes: Stronger and Faster Approximations
This paper reports on and discusses three notions of approximation for Labelled Markov Processes that have been developed last year. The three schemes are improvements over former...
Vincent Danos, Josee Desharnais