System Model-Based Definition of Modeling Language Semantics
This work addresses the challenge of semantics definition for modeling languages, which is incremental as it builds on existing declarative approaches but enhances reusability and tool support.
The paper tackles the problem of defining semantics for object-oriented modeling languages by introducing a system model as a semantic domain, enabling support for underspecified and incomplete models and facilitating integration across languages.
In this paper, we present an approach to define the semantics for object-oriented modeling languages. One important property of this semantics is to support underspecified and incomplete models. To this end, semantics is given as predicates over elements of the semantic domain. This domain is called the system model which is a general declarative characterization of object systems. The system model is very detailed since it captures various relevant structural, behavioral, and interaction aspects. This allows us to re-use the system model as a domain for various kinds of object-oriented modeling languages. As a major consequence the integration of language semantics is straight-forward. The whole approach is supported by tools that do not constrain the semantics definition's expressiveness and flexibility while making it machinecheckable.