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.
@article{arxiv.1909.02265,
title = {Towards Task-Oriented Dialogue in Mixed Domains},
author = {Tho Luong Chi and Phuong Le-Hong},
journal= {arXiv preprint arXiv:1909.02265},
year = {2019}
}