Multi-Label Classification
暂无分享,去创建一个
Humans naturally associate an object with more than one concept, i.e., label (also known as a category, tag, or genre). Adding labels to data collections can greatly facilitate retrieval and organization. This is a vital task with the everincreasing collections of data being created and accessed each day. In 2010 it was estimated that we were creating the same quantity of data every two days, as we created from the dawn of time up until 2003. Multi-label classification is a way to learn label multi-label associations and, importantly, assign labels to new data automatically.
[1] Dirk Vriens. Information and Communications Technology for Competitive Intelligence , 2003 .
[2] Dirk Vriens,et al. The Source Map: A Means to Support Collection Activities , 2003 .
[3] I. Mezgár,et al. Integration of ICT in Smart Organizations , 2006 .