Towards Task-Oriented Dialogue in Mixed Domains

09/05/2019
by   Tho Luong Chi, et al.
0

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 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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset