Memory-augmented Dialogue Management for Task-oriented Dialogue Systems

TL;DR

This paper introduces MAD, a memory-augmented dialogue management model that effectively captures long-range dialogue history using specialized memory structures, leading to improved task-oriented dialogue system performance.

Contribution

The paper presents a novel MAD model with a memory controller, slot-value memory, and external memory, enhancing dialogue state tracking and context representation.

Findings

Achieves state-of-the-art performance on dialogue management tasks.

Outperforms existing baselines in accuracy and efficiency.

Effectively models long-range dialogue history using memory structures.

Abstract

Dialogue management (DM) decides the next action of a dialogue system according to the current dialogue state, and thus plays a central role in task-oriented dialogue systems. Since dialogue management requires to have access to not only local utterances, but also the global semantics of the entire dialogue session, modeling the long-range history information is a critical issue. To this end, we propose a novel Memory-Augmented Dialogue management model (MAD) which employs a memory controller and two additional memory structures, i.e., a slot-value memory and an external memory. The slot-value memory tracks the dialogue state by memorizing and updating the values of semantic slots (for instance, cuisine, price, and location), and the external memory augments the representation of hidden states of traditional recurrent neural networks through storing more context information. To update the dialogue state efficiently, we also propose slot-level attention on user utterances to extract specific semantic information for each slot. Experiments show that our model can obtain state-of-the-art performance and outperforms existing baselines.