Addressing Objects and Their Relations: The Conversational Entity Dialogue Model
This work addresses the limitation of existing dialogue systems in handling complex relational structures, which is incremental as it builds on multi-domain models.
The authors tackled the problem of modeling complex dialogue structures like relations in spoken dialogue systems by proposing a novel entity-centered dialogue model. They demonstrated that a trained policy using these relations outperforms a multi-domain baseline and enables the system to process and address relations in user input.
Statistical spoken dialogue systems usually rely on a single- or multi-domain dialogue model that is restricted in its capabilities of modelling complex dialogue structures, e.g., relations. In this work, we propose a novel dialogue model that is centred around entities and is able to model relations as well as multiple entities of the same type. We demonstrate in a prototype implementation benefits of relation modelling on the dialogue level and show that a trained policy using these relations outperforms the multi-domain baseline. Furthermore, we show that by modelling the relations on the dialogue level, the system is capable of processing relations present in the user input and even learns to address them in the system response.