Sciweavers

395 search results - page 67 / 79
» Learning to rank with partially-labeled data
Sort
View
PKDD
2010
Springer
168views Data Mining» more  PKDD 2010»
14 years 10 months ago
Bayesian Knowledge Corroboration with Logical Rules and User Feedback
Current knowledge bases suffer from either low coverage or low accuracy. The underlying hypothesis of this work is that user feedback can greatly improve the quality of automatica...
Gjergji Kasneci, Jurgen Van Gael, Ralf Herbrich, T...
JMLR
2010
117views more  JMLR 2010»
14 years 6 months ago
Exploiting the High Predictive Power of Multi-class Subgroups
Subgroup discovery aims at finding subsets of a population whose class distribution is significantly different from the overall distribution. A number of multi-class subgroup disc...
Tarek Abudawood, Peter A. Flach
ICDM
2009
IEEE
211views Data Mining» more  ICDM 2009»
15 years 6 months ago
Discovering Organizational Structure in Dynamic Social Network
—Applying the concept of organizational structure to social network analysis may well represent the power of members and the scope of their power in a social network. In this pap...
Jiangtao Qiu, Zhangxi Lin, Changjie Tang, Shaojie ...
WSDM
2009
ACM
191views Data Mining» more  WSDM 2009»
15 years 6 months ago
Generating labels from clicks
The ranking function used by search engines to order results is learned from labeled training data. Each training point is a (query, URL) pair that is labeled by a human judge who...
Rakesh Agrawal, Alan Halverson, Krishnaram Kenthap...
CIKM
2011
Springer
13 years 11 months ago
A probabilistic method for inferring preferences from clicks
Evaluating rankers using implicit feedback, such as clicks on documents in a result list, is an increasingly popular alternative to traditional evaluation methods based on explici...
Katja Hofmann, Shimon Whiteson, Maarten de Rijke