Sciweavers

118 search results - page 7 / 24
» Unlabeled data improves word prediction
Sort
View
CIKM
2011
Springer
13 years 11 months ago
Semi-supervised multi-task learning of structured prediction models for web information extraction
Extracting information from web pages is an important problem; it has several applications such as providing improved search results and construction of databases to serve user qu...
Paramveer S. Dhillon, Sundararajan Sellamanickam, ...
CVPR
2008
IEEE
16 years 1 months ago
Transfer learning for image classification with sparse prototype representations
To learn a new visual category from few examples, prior knowledge from unlabeled data as well as previous related categories may be useful. We develop a new method for transfer le...
Ariadna Quattoni, Michael Collins, Trevor Darrell
CVPR
2009
IEEE
16 years 6 months ago
What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations
Active learning strategies can be useful when manual labeling effort is scarce, as they select the most informative examples to be annotated first. However, for visual category ...
Sudheendra Vijayanarasimhan (University of Texas a...
ICDAR
2011
IEEE
13 years 11 months ago
Co-training for Handwritten Word Recognition
—To cope with the tremendous variations of writing styles encountered between different individuals, unconstrained automatic handwriting recognition systems need to be trained on...
Volkmar Frinken, Andreas Fischer, Horst Bunke, Ali...
EMNLP
2011
13 years 11 months ago
Universal Morphological Analysis using Structured Nearest Neighbor Prediction
In this paper, we consider the problem of unsupervised morphological analysis from a new angle. Past work has endeavored to design unsupervised learning methods which explicitly o...
Young-Bum Kim, João Graça, Benjamin ...