NIPS
2004
13 years 10 months ago
2004
In the context of binary classification, we define disagreement as a measure of how often two independently-trained models differ in their classification of unlabeled data. We exp...
NIPS
2004
13 years 10 months ago
2004
We consider the semi-supervised learning problem, where a decision rule is to be learned from labeled and unlabeled data. In this framework, we motivate minimum entropy regulariza...
CASCON
2001
13 years 10 months ago
2001
The main problems in text classification are lack of labeled data, as well as the cost of labeling the unlabeled data. We address these problems by exploring co-training - an algo...
FLAIRS
2004
13 years 10 months ago
2004
Using unlabeled data to help supervised learning has become an increasingly attractive methodology and proven to be effective in many applications. This paper applies semi-supervi...
EACL
2006
ACL Anthology
13 years 10 months ago
2006
ACL Anthology
Current Named Entity Recognition systems suffer from the lack of hand-tagged data as well as degradation when moving to other domain. This paper explores two aspects: the automati...
ACL
2006
13 years 10 months ago
2006
This paper proposes a semi-supervised boosting approach to improve statistical word alignment with limited labeled data and large amounts of unlabeled data. The proposed approach ...
AAAI
2006
13 years 10 months ago
2006
We present a novel framework for multi-label learning that explicitly addresses the challenge arising from the large number of classes and a small size of training data. The key a...
SDM
2007
SIAM
13 years 10 months ago
2007
SIAM
Feature selection is an important task in effective data mining. A new challenge to feature selection is the so-called “small labeled-sample problem” in which labeled data is...
NIPS
2007
13 years 10 months ago
2007
We show how to use unlabeled data and a deep belief net (DBN) to learn a good covariance kernel for a Gaussian process. We first learn a deep generative model of the unlabeled da...
NIPS
2007
13 years 10 months ago
2007
Semi-supervised methods use unlabeled data in addition to labeled data to construct predictors. While existing semi-supervised methods have shown some promising empirical performa...