Towards Task-Oriented Dialogue in Mixed Domains
This work addresses the problem of improving dialogue systems for mixed-domain applications, such as commercial chatbots, but it appears incremental as it builds on existing state-of-the-art systems.
The paper tackles task-oriented dialogue in mixed domains by showing that a specialized state tracking component outperforms an end-to-end system, and proposes a hybrid system that improves belief tracking accuracy by about 28% on a standard dataset.
This work investigates the task-oriented dialogue problem in mixed-domain settings. We study the effect of alternating between different domains in sequences of dialogue turns using two related state-of-the-art dialogue systems. We first show that a specialized state tracking component in multiple domains plays an important role and gives better results than an end-to-end task-oriented dialogue system. We then propose a hybrid system which is able to improve the belief tracking accuracy of about 28% of average absolute point on a standard multi-domain dialogue dataset. These experimental results give some useful insights for improving our commercial chatbot platform FPT.AI, which is currently deployed for many practical chatbot applications.