Abstract: Studies on Semantic Annotation reveal how trying to match heterogeneous requirements leads to divergent methodologies, models and processes for annotation management and exchange. Community efforts towards the development of shared solutions are important to reduce the “entropy ” of the field; nonetheless, any agreement on the ultimate annotation system is unlikely to be achieved. We propose a solution to this problem by defining a comprehensive framework, unbound to any specific design/annotation model, and instantiable into concrete system implementations, to meet different requirements. Towards this goal, we commit to fairly general assumptions, valid across disparate systems and not excessively constraining. Firstly, most systems deal with combined management of ontologies and Web content. Secondly, these systems can be described through a common behavioural model, in terms of an assignment of handlers to predetermined events. This behavioural model can be then enriched through progressive levels of specification, thus fostering a convention-over-configuration approach in detailing its characteristics. Then, recurring design fragments can be identified, in order to provide abstractions and specifications for the definition of concrete handlers. 1

Both the multilingual aspects which characterize the (Semantic) Web and the demand for more easy-to-share forms of knowledge representation, being equally accessible by humans and machines, push the need for a more “linguistically aware” approach to ontology development. Ontologies should thus express knowledge by associating formal content with explicative linguistic expressions, possibly in different languages. By adopting such an approach, the intended meaning of concepts and roles becomes more clearly expressed for humans, thus facilitating (among others) reuse of existing knowledge, while automatic content mediation between autonomous information sources gets far more chances than otherwise. In past work we introduced OntoLing [7], a Protégé plug-in offering a modular and scalable framework for performing manual annotation of ontological data with information from different, heterogeneous linguistic resources. We present now an improved version of OntoLing, which supports the user with automatic suggestions for enriching ontologies with linguistic content. Different specific linguistic enrichment problems are discussed and we show how they have been tackled considering both algorithmic aspects and profiling of user interaction inside the OntoLing framework. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.