843 search results - page 56 / 169 » Learning aspect models with partially labeled data |
117
click to vote
NIPS
2001
15 years 5 months ago
2001
We propose the framework of mutual information kernels for learning covariance kernels, as used in Support Vector machines and Gaussian process classifiers, from unlabeled task da...
160
click to vote
ICML
2008
IEEE
2008
IEEE
A unified architecture for natural language processing: deep neural networks with multitask learning
16 years 4 months ago
We describe a single convolutional neural network architecture that, given a sentence, outputs a host of language processing predictions: part-of-speech tags, chunks, named entity...
125
click to vote
ICDM
2007
IEEE
15 years 10 months ago
2007
IEEE
We explore the problem of budgeted machine learning, in which the learning algorithm has free access to the training examples’ labels but has to pay for each attribute that is s...
146
click to vote
AAAI
2006
15 years 5 months ago
2006
This paper presents multi-conditional learning (MCL), a training criterion based on a product of multiple conditional likelihoods. When combining the traditional conditional proba...
115
click to vote
MVA
2007
15 years 5 months ago
2007
For a social robot, the ability of learning tasks via human demonstration is very crucial. But most current approaches suffer from either the demanding of the huge amount of label...