In many important text classification problems, acquiring class labels for training documents is costly, while gathering large quantities of unlabeled data is cheap. This paper shows that the accuracy of text classifiers trained with a small number of labeled documents can be improved by augmenting this small training set with a large pool of unlabeled documents. We present a theoretical argume...

Public archives contain large and continuously growing volumes of electronically available text documents. In many countries, public authorities are required by law to publish certain data to satisfy the information needs of the general public. In contrast to plain text documents, semantically tagged XML documents along with appropriate query languages largely facilitate searching and browsing ...

Text categorization is intrinsically a supervised learning task, which aims at relating a given text document to one or more predefined categories. Unfortunately, labeling such databases of documents is a painful task. We present in this paper a method that takes advantage of huge amounts of unlabeled text documents available in digital format, to counter balance the relatively smaller availabl...

Documents can be represented as structures with a hierarchial arrangement of text and non-text nodes, where nodes are labeled by category names such as paragraph and section. Representing documents this way is a natural consequence of using the Standard Generalized Markup Language(SGML) to encode text documents which has many applications in different areas. There are many circumstances in whic...

Due to increasing use of internet and online technologies or online data, there is vast increase in the electronic documents. When a data is being retrieved from such a huge collection of electronic documents, hundreds and thousands of documents are retrieved. Hence, for user, it is not possible to read all the retrieved documents. Also, these documents contain redundant information. In such si...