Extending the Unified Modeling Language for Ontology Development Kenneth Baclawski 2 , Mieczyslaw K. Kokar 2 , Paul A. Kogut 1 , Lewis Hart 5 , Jeffrey Smith 3 , Jerzy Letkowski 4 , and Pat Emery 5 1 Lockheed Martin Management and Data Systems 2 Northeastern University 3 Mercury Computer 4 Western New England College 5 GRC International Abstract. There is rapidly growing momentum for web enabled agents that reason about and dynam- ically integrate the appropriate knowledge and services at run-time. The dynamic integration of knowl- edge and services depends on the existence of explicit declarative semantic models (ontologies). We have been building tools for ontology development based on the Unified Modeling Language (UML). This allows the many mature UML tools, models and expertise to be applied to knowledge representation systems, not only for visualizing complex ontologies but also for managing the ontology development process. UML has many features, such as profiles, global modularity and extension mechanisms that are not generally available in most ontology languages. However, ontology languages have some fea- tures that UML does not support. Our paper identifies the similarities and differences (with examples) between UML and the ontology languages RDF and DAML+OIL. To reconcile these differences, we propose a modification to the UML metamodel to address some of the most problematic differences. One of these is the ontological concept variously called a property, relation or predicate. This notion corresponds to the UML concepts of association and attribute. In ontology languages properties are first-class modeling elements, but UML associations and attributes are not first-class. Our proposal is backward-compatible with existing UML models while enhancing its viability for ontology modeling. While we have focused on RDF and DAML+OIL in our research and development activities, the same issues apply to many of the knowledge representation languages. This is especially the case for semantic network and concept graph approaches to knowledge representations. Keywords: ontology, semantic web, agents, OO modeling, UML, RDF, DAML. 1 Introduction and Motivation Representing knowledge is an important part of any knowledge-based system. In particular, all artificial intelligence systems must support some kind of knowledge representation (KR). Because of this, many KR languages have been developed. For an excellent introduction to knowledge representations and ontologies see [29]. Expressing knowledge in machine-readable form requires that it be represented as data. There- fore it is not surprising that KR languages and data languages have much in common, and both kinds of language have borrowed ideas and concepts from each other. Inheritance in object-oriented programming and modeling languages was derived to a large extent from the corresponding notion in KR languages. KR languages can be given a rough classification into three categories: – Logical languages. These languages express knowledge as logical statements. One of the best- known examples of such a KR language is the Knowledge Interchange Format (KIF) [12].