Modeling Multi-Action Policy for Task-Oriented Dialogues
This work addresses a bottleneck in task-oriented dialogue systems by improving efficiency and user experience, though it is incremental as it builds on existing methods.
The paper tackles the problem of dialogue management in task-oriented systems by proposing a model that predicts multiple policy actions per turn, rather than one, to reduce unwanted interactions and errors; experimental results show that the novel gCAS model outperforms other approaches.
Dialogue management (DM) plays a key role in the quality of the interaction with the user in a task-oriented dialogue system. In most existing approaches, the agent predicts only one DM policy action per turn. This significantly limits the expressive power of the conversational agent and introduces unwanted turns of interactions that may challenge users' patience. Longer conversations also lead to more errors and the system needs to be more robust to handle them. In this paper, we compare the performance of several models on the task of predicting multiple acts for each turn. A novel policy model is proposed based on a recurrent cell called gated Continue-Act-Slots (gCAS) that overcomes the limitations of the existing models. Experimental results show that gCAS outperforms other approaches. The code is available at https://leishu02.github.io/