Generating Dialogue Agents via Automated Planning
This addresses the problem of enabling more advanced, personalized, and context-dependent conversational interactions for users in domains such as customer support and coaching, though it appears incremental as it builds on existing planning techniques.
The paper tackles the challenge of creating complex multi-turn dialogue systems for applications like career coaching and trip planning by using domain-independent AI planning to automatically generate customized dialogue plans, and demonstrates viability through use cases and product integration.
Dialogue systems have many applications such as customer support or question answering. Typically they have been limited to shallow single turn interactions. However more advanced applications such as career coaching or planning a trip require a much more complex multi-turn dialogue. Current limitations of conversational systems have made it difficult to support applications that require personalization, customization and context dependent interactions. We tackle this challenging problem by using domain-independent AI planning to automatically create dialogue plans, customized to guide a dialogue towards achieving a given goal. The input includes a library of atomic dialogue actions, an initial state of the dialogue, and a goal. Dialogue plans are plugged into a dialogue system capable to orchestrate their execution. Use cases demonstrate the viability of the approach. Our work on dialogue planning has been integrated into a product, and it is in the process of being deployed into another.