Abstract: Intelligent and dialogue systems highly utilise natural language interfaces. Such systems do not only process linguistic questions, but also formulate proper linguistic responses. Often neglected and important aspect of such responses lies in the ability to express and communicate systems internal beliefs. The proposed model fills in the current research gap in the grounding theory by enriching empirical experiences with hierarchical semantic structures in establishing agents internal belief stance. Such an extension significantly influences the process of grounding and allows for a dedicated computational mechanism of moving the conversations focus, which is incorporated into grounding mechanisms and fully presented.
Loading