Analyzing the Effectiveness and Applicability of Co-training Export

by: Kamal Nigam, Rayid Ghani

In CIKM (2000), pp. 86-93.

[Posts]

View FullText article

CiteSeer (at Penn State), CiteSeer (at MIT), CiteSeer (at Zurich), CiteSeer (at Singapore), Rent at DeepDyve

bpacker's tags for this article

cotraining probabilistic-models

Reviews [Write a review of this article]

Find related articles from these CiteULike users

davidr, buescher76, mukundn, bpacker

Find related articles with these CiteULike tags

cotraining, co-training, learning, multi-view, probabilistic-models, semisupervisedlearning, unsupervised

Abstract

Recently there has been significant interest in supervised learning algorithms that combine labeled and unlabeled data for text learning tasks. The co-training setting [1] applies to datasets that have a natural separation of their features into two disjoint sets. We demonstrate that when learning from labeled and unlabeled data, algorithms explicitly leveraging a natural independent split of the features outperform algorithms that do not. When a natural split does not exist, co-training...

@inproceedings{citeulike:142759, abstract = {Recently there has been significant interest in supervised learning algorithms that combine labeled and unlabeled data for text learning tasks. The co-training setting [1] applies to datasets that have a natural separation of their features into two disjoint sets. We demonstrate that when learning from labeled and unlabeled data, algorithms explicitly leveraging a natural independent split of the features outperform algorithms that do not. When a natural split does not exist, co-training...}, author = {Nigam, Kamal and Ghani, Rayid}, booktitle = {CIKM}, citeulike-article-id = {142759}, citeulike-linkout-0 = {http://citeseer.ist.psu.edu/nigam00analyzing.html}, citeulike-linkout-1 = {http://citeseer.lcs.mit.edu/nigam00analyzing.html}, citeulike-linkout-2 = {http://citeseer.ifi.unizh.ch/nigam00analyzing.html}, citeulike-linkout-3 = {http://citeseer.comp.nus.edu.sg/nigam00analyzing.html}, keywords = {cotraining, probabilistic-models}, pages = {86--93}, posted-at = {2008-01-23 16:45:13}, priority = {3}, title = {Analyzing the Effectiveness and Applicability of Co-training}, url = {http://citeseer.ist.psu.edu/nigam00analyzing.html}, year = {2000} }

RIS record

TY - CONF ID - citeulike:142759 L3 - citeulike-article-id:142759 N2 - Recently there has been significant interest in supervised learning algorithms that combine labeled and unlabeled data for text learning tasks. The co-training setting [1] applies to datasets that have a natural separation of their features into two disjoint sets. We demonstrate that when learning from labeled and unlabeled data, algorithms explicitly leveraging a natural independent split of the features outperform algorithms that do not. When a natural split does not exist, co-training... EP - 93 TI - Analyzing the Effectiveness and Applicability of Co-training T2 - CIKM SP - 86 KW - cotraining KW - probabilistic-models AU - Nigam, Kamal AU - Ghani, Rayid PY - 2000/// UR - http://citeseer.ist.psu.edu/nigam00analyzing.html ER -

vision	44
probabilistic-models	21
statistics	13
classification	13
sparse-coding	12
boosting	11
caltech	10
cotraining	9
recognition	9
v1	8
hierarchy	8
social-science	8
nlp	7
v2	7
topic	7
feedback	7
evolution	7
orientation	7
contour	6
semisupervised-learning	6
algorithms	6
complex-cell	6
ncrf	5
product-of-experts	5
dimensionality-reduction	4
parental-investment	4
lasso	4
lda	4
curvature	3
learning-theory	3
ica	3
phase-learning	3
sna	3
collaborative-filtering	3
bag-of-patches	3
trees	2
color	2
priors	2
endstopping	2
regularization	2
object-detection	2
continuation-methods	2
correspondence	1
optimization	1
racism	1
medical	1
feedforward	1
math	1
hmm	1
pos	1

Analyzing the Effectiveness and Applicability of Co-training Export

Citation Format