PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Simple classification into large topic ontology of Web documents
Marko Grobelnik and Dunja Mladenić
In: ITI 2005, 20-24 June, Cavtat, Croatia.

Abstract

The paper presents an approach to classifying Web documents into large topic ontology. The main emphasis is on having a simple approach appropriate for handling a large ontology and providing it with enriched data by including additional information on the Web page context obtained from the link structure of the Web. The context is generated form the in-coming and out-going links of the Web document we want to classify (the target document), meaning that for representing a document we use, not only text of the document itself, but also the text from the documents pointing to the target document as well as the text form the documents that the target document is pointing to. The idea is that providing enriched data is compensating for the simplicity of the approach while keeping it efficient and capable of handling large topic ontology.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
Information Retrieval & Textual Information Access
ID Code:844
Deposited By:Dunja Mladenić
Deposited On:09 July 2005