VOnDA: A Framework for Ontology-Based Dialogue Management
This addresses the need for reliable and adaptive dialogue systems in critical domains like healthcare, though it appears incremental as it builds on existing ontology-based methods.
The authors tackled the problem of dialogue management in social communication systems, such as those used in health or elderly care, by developing VOnDA, a framework that uses RDF/OWL for specification and memory to ensure low error margins and high control.
We present VOnDA, a framework to implement the dialogue management functionality in dialogue systems. Although domain-independent, VOnDA is tailored towards dialogue systems with a focus on social communication, which implies the need of long-term memory and high user adaptivity. For these systems, which are used in health environments or elderly care, margin of error is very low and control over the dialogue process is of topmost importance. The same holds for commercial applications, where customer trust is at risk. VOnDA's specification and memory layer relies upon (extended) RDF/OWL, which provides a universal and uniform representation, and facilitates interoperability with external data sources, e.g., from physical sensors.