Sciweavers

5621 search results - page 109 / 1125
» Augmentation of adaptation data
Sort
View
ACL
2009
15 years 2 months ago
Updating a Name Tagger Using Contemporary Unlabeled Data
For many NLP tasks, including named entity tagging, semi-supervised learning has been proposed as a reasonable alternative to methods that require annotating large amounts of trai...
Cristina Mota, Ralph Grishman
ICASSP
2011
IEEE
14 years 8 months ago
Using stacked transformations for recognizing foreign accented speech
A common problem in speech recognition for foreign accented speech is that there is not enough training data for an accent-specific or a speaker-specific recognizer. Speaker ada...
Peter Smit, Mikko Kurimo
SIGMOD
2003
ACM
126views Database» more  SIGMOD 2003»
16 years 4 months ago
Issues in data stream management
Traditional databases store sets of relatively static records with no pre-defined notion of time, unless timestamp attributes are explicitly added. While this model adequately rep...
Lukasz Golab, M. Tamer Özsu
CVPR
2008
IEEE
15 years 10 months ago
Global data association for multi-object tracking using network flows
We propose a network flow based optimization method for data association needed for multiple object tracking. The maximum-a-posteriori (MAP) data association problem is mapped in...
Li Zhang, Yuan Li, Ramakant Nevatia
SAMOS
2010
Springer
15 years 2 months ago
Programming multi-core architectures using Data-Flow techniques
Abstract—In this paper we present a Multithreaded programming methodology for multi-core systems that utilizes DataFlow concurrency. The programmer augments the program with macr...
Samer Arandi, Paraskevas Evripidou