An adaptive optimisation method for automatic lightweight ontology extraction

It is well known how the use of additional knowledge, coded through ontologies, can improve the quality of the results obtained, in terms of user satisfaction, when seeking information on the web. The choice of a knowledge base, as long as it is reduced to small domains, is still manageable in a semi-automatic mode. However, in wider contexts, where a higher scalability is required, a fully automatic procedure is needed. In this paper, we show how a procedure to extract an ontology from a collection of documents can be completely automatised by making use of an optimization procedure. To this aim, we have defined a suitable fitness function and we have employed a Random Mutation Hill-Climbing algorithm to explore the solution space in order to evolve a near-optimal solution. The experimental findings show that our method is effective. © 2011 Springer-Verlag Berlin Heidelberg.