Leveraging Sub-class Partition Information in Binary Classification and Its Application
Citation:
Leveraging Sub-class Partition Information in Binary Classification and Its Application, Max Bramer, Richard Ellis and Miltos Petridis, Research and Development in Intelligent Systems XXVI, London, Springer, 2009, 299 - 304, Baoli Li and Carl VogelDownload Item:
AI-2009-v0.9.pdf (Published (author's copy) - Peer Reviewed) 79.62Kb
Abstract:
Sub-class partition information within positive and negative classes is
often ignored by a binary classifier, even when these detailed background
information is available at hand. It is expected that this kind of additional
information can help to improve the differentiating capacity of a binary classifier.
In this paper, a binary classification strategy via multi-class categorization is
proposed to leverage sub-class partition information when they are available.
Empirical studies on the 20 newsgroups dataset demonstrate the benefits of this
strategy. Furthermore, a preliminary application of this binary classification
strategy for multi-label classification problem is given with promising results.
Sponsor
Grant Number
Science Foundation Ireland (SFI)
Author's Homepage:
http://people.tcd.ie/vogelDescription:
PUBLISHEDProceedings of AI-2009, The Twenty-ninth SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence
London
Author: VOGEL, CARL
Other Titles:
Research and Development in Intelligent Systems XXVIPublisher:
SpringerType of material:
Book ChapterCollections:
Availability:
Full text availableKeywords:
Computer Science, Computer ScienceSubject (TCD):
Intelligent Content & Communications , Smart & Sustainable Planet , Computational linguisticsISSN:
978 1 84882 982 4Licences: