PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Automated Knowledge Discovery in Advanced Knowledge Management
Marko Grobelnik and Dunja Mladenić
Journal of Knowledge Management Volume 9, Number 5, pp. 132-149, 2005.


Knowledge Management is a discipline with many faces – among very provocative ones is the research area dealing with automatic discovery of the hidden truth within the data describing the world around us. The basic idea of knowledge discovery is to let the computer search for the knowledge whereas the humans give just broad directions about where and how to search. Surprisingly, it is often the case that already relatively simple techniques are able to uncover useful hidden truth beneath the surface of the known facts and relationships. In this paper we present approaches of various research subfields working in the area of knowledge discovery from different sources (such as databases, documents, networks, etc), in different forms (e.g. probabilistic, various kinds of logic, visualizations), on different scale (small data-sets or terra bytes), and for different purpose (e.g. prediction, segmentation, explanation). Knowledge Discovery will be presented in the light of one of the key paradigms within Knowledge Management with the emphasis on the cases where humans need to go steps further from what could be captured manually.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
Information Retrieval & Textual Information Access
ID Code:1412
Deposited By:Dunja Mladenić
Deposited On:28 November 2005