DMCA
Committee-Based Sample Selection For Probabilistic Classifiers (1999)
Cached
Download Links
- [www.cs.cmu.edu]
- [www.cs.cmu.edu]
- [www.jair.org]
- [jair.org]
- [arxiv.org]
- DBLP
Other Repositories/Bibliography
| Venue: | Journal of Artificial Intelligence Research |
| Citations: | 65 - 0 self |
BibTeX
@ARTICLE{Argamon-Engelson99committee-basedsample,
author = {Shlomo Argamon-Engelson and Ido Dagan},
title = {Committee-Based Sample Selection For Probabilistic Classifiers},
journal = {Journal of Artificial Intelligence Research},
year = {1999},
volume = {11},
pages = {335--360}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In many real-world learning tasks it is expensive to acquire a sufficient number of labeled examples for training. This paper investigates methods for reducing annotation cost by sample selection. In this approach, during training the learning program examines many unlabeled examples and selects for labeling only those that are most informative at each stage. This avoids redundantly labeling examples that contribute little new information. Our work follows on previous research on Query By Committee, and extends the committee-based paradigm to the context of probabilistic classification. We describe a family of empirical methods for committee-based sample selection in probabilistic classification models, which evaluate the informativeness of an example by measuring the degree of disagreement between several model variants. These variants (the committee) are drawn randomly from a probability distribution conditioned by the training set labeled so far. The method was applied to...
Keyphrases
committee-based sample selection probabilistic classifier sample selection training set probability distribution labeling example probabilistic classification annotation cost probabilistic classification model empirical method several model variant previous research little new information committee-based paradigm labeled example sufficient number program examines many unlabeled example
