Dependency-based mapping between symbolic language and Extended Conceptual Graph

The goal of our research is to develop a grammar induction system that can assign descriptive sentences to ontology models represented by an extended conceptual graph (ECG) which is a conceptual modeling language for describing the semantics of an agentpsilas internal knowledge model. In the proposed system, the ECG model of the agent is converted into a symbolic language sentence. For this, the system should learn first the rules of association between sentence elements and ECG model elements. In order to learn the grammar rules, the system should be presented with training sentences carrying information on the ordering and inflection of words. This paper presents the training algorithm of the grammar induction system in details.