In the quest of specific-domain ontology components for the semantic web JRG Pulido * SBF Flores PD Reyes RA Diaz JJC Castillo Faculty of Telematics, University of Colima, M´ exico {jrgp,medusa,damian,acosta,juancont}@ucol.mx Keywords: Ontology Learning, Semantic Web, Self-Organizing Maps Abstract— This paper describes an approach we have been using to identify specific-domain ontology compo- nents by using Self-Organizing Maps. These components are clustered together in a natural way according to their similarity. The knowledge maps, as we call them, show col- ored regions containing knowledge components that may be used to populate an specific-domain ontology. Later, these ontology may be used by software agents to carry out basic reasoning task on our behalf. In particular, we deal with the issue of not constructing the ontology from scratch, our approach helps us to speed up the ontology creation process. 1 Introduction The semantic web, requires that the information contained into digital archives is structured [4]. In the last few years a number of proposals on how to represent knowledge via ontology languages have paraded [42, 10, 17, 15, 30]. Now that OWL has become an standard [25], the real challenge has started. Slowly but surely the web is to be populated with structured knowledge that will allow software agents to act on our behalf. Converting the current web into the next generation one, the Semantic Web, is to take much longer if no semi-automatic approaches are taken into ac- count to carry out this enterprise. This is what our paper is all about. The remainder of this paper is organized as follows. In section 2 some related work is introduced. Our approach is outlined in section 3. Results are presented in section 4, and conclusions and further work in section 5. 2 Related Work Vast amounts of knowledge are currently available on the Internet and its quantity is growing rapidly. This has un- derlined the weakness of current mechanisms and tech- niques used to give users access to this knowledge. The difficulty of extracting, filtering, and organizing knowledge from expert domains has challenged the research commu- nity which is now extremely interested in reusing knowl- edge. The fundamental problem is how to extract for- mal and consistent knowledge representations suitable for * Corresponding author, Tel/fax: +52 312 316 1075 specialised tasks such as inference. In the context of the semantic web, one of the most important challenges is the mapping of large amounts of unstructured information, suitable for humans,into formal representation of knowl- edge [4]. In the next subsections we have a brief look at some related work on Ontologies and Self-Organizing Maps which are the framework of our approach. 2.1 Ontologies An ontology may be referred to as an agreed conceptualiza- tion. In other words, it is a set of elements that, as a whole, allow us represent real world domains, an academic one for instance. Must be said that representing knowledge about a domain as an ontology is a challenging process which is difficult to achieve in a consistent and rigorous way. It is easy to lose consistency and to introduce ambiguity and confusion [3]. The ontology life cycle usually requires the following [8, 29, 9, 7, 46] activities (Fig.1): Gathering The acquisition and collection of the knowl- edge from the domain in which we are interested. It usually involves dealing with unstructured data in natural language from digital archives. Extraction This requires background knowledge for cre- ating taxonomies of the domain in a semi-automatic way. Learning techniques may be applied by the knowledge en- gineer for this task. Organization Imposing a structure on the knowledge ac- quired and generating formal representations of it for later being used by software agents or humans. Merging Defining mapping rules to facilitate interlingua exchange relating information from one context to another. This activity is as important as Extraction. It can be re- ferred to as finding commonalities between two knowledge bases and deriving a new knowledge base. Refinement Improving structure and content of the knowledge about the domain by eliciting knowledge from the domain experts. It amends the knowledge at a finer granularity level.