125 search results - page 6 / 25 » Combining labeled and unlabeled data with word-class distrib... |
105
click to vote
KDD
2008
ACM
15 years 10 months ago
2008
ACM
The input to an algorithm that learns a binary classifier normally consists of two sets of examples, where one set consists of positive examples of the concept to be learned, and ...
KDD
2008
ACM
15 years 10 months ago
2008
ACM
This paper addresses the repeated acquisition of labels for data items when the labeling is imperfect. We examine the improvement (or lack thereof) in data quality via repeated la...
ICASSP
2011
IEEE
14 years 1 months ago
2011
IEEE
Current hidden Markov acoustic modeling for large vocabulary continuous speech recognition (LVCSR) relies on the availability of abundant labeled transcriptions. Given that speech...
ICML
2005
IEEE
15 years 10 months ago
2005
IEEE
We introduce a Bayesian model, BayesANIL, that is capable of estimating uncertainties associated with the labeling process. Given a labeled or partially labeled training corpus of...
86
Voted
JMLR
2010
14 years 4 months ago
2010
In this paper, we present an overview of generalized expectation criteria (GE), a simple, robust, scalable method for semi-supervised training using weakly-labeled data. GE fits m...