VOnDA: A Framework for Ontology-Based Dialogue Management

TL;DR

VOnDA is a flexible, ontology-based dialogue management framework designed for social communication systems, emphasizing long-term memory, user adaptivity, and high reliability in sensitive applications.

Contribution

It introduces a domain-independent framework utilizing RDF/OWL for dialogue management, tailored for social and critical applications requiring high accuracy and adaptability.

Findings

Supports interoperability with external data sources

Enhances dialogue control in sensitive environments

Utilizes semantic web technologies for flexibility

Abstract

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.