… text documents into two disjoint classes. Two sample sets of training examples (text documents)
… classify unseen text documents. This is a typical case of supervised “crisp” classification. …

… text clustering which are the detection of non-disjoint groups and the representation of
textual data. In fact, a text document … results when the number of classes is not large.Experiments …

… Only if we define these classes as being disjoint, the … .icio.us documents tagged with the
corresponding class labels. … tion 3.1) or from a given corpus of text documents. In the latter case, …

… text document objects. Pictures are only considered as a whole. Different granularities for
text elements are considered, like characters, words or text-… can be situated are disjoint. The …

… attributes, the disjoint features selected for superand sub-classes by our method can be quite
intuitive. … of text documents. Concretely, they propose an orthogonal regularizer ∑ij Kij|wT …

… of a particular text document d to generate a pseudo-document 'd … Further, in disjoint partition,
the text document will appear in … It is then used for predicting classes of unseen documents. …

… In standard setting of SSL, documents D can be divided into two disjoint subsets: DL … Then
we calculate the membership degree of classes for each document and assign class labels …

… tb are disjoint, where 1 means the two objects are the same and 0 means they are completely
… set and nh i is the number of documents from the hth class that were assigned to cluster Ci. …

… text documents in different languages, as described in the later sections of this paper, it is
called cross-language text … All 1382 documents are manually labeled into five disjoint classes (…

… Other processes in FIHC, such as making clusters disjoint and pruning, are … documents of
class i, n j is the number of documents of cluster j, and n ij is the number of documents of class i …