Open Set Text Classification Using Neural Networks
In a closed set environment, classiﬁers are trained on examples from a number of known classesandtestedwithunseenexamplesbelongingtothesamesetofknownclasses. However, in most real-world scenarios, a trained classiﬁer is likely to come across novel examples that do not belong to any of the known classes. Such examples should ideally be categorized asbelonging toan unknown class. The goal of an open set classiﬁer isto identify and classify test examples of classes unseen during training. The classiﬁer should be able to declare that a test example belongs to a class it does not know when necessary, ...
(For more, see "View full record.")