Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking

TL;DR

This paper introduces a novel approach to multi-domain dialogue state tracking that incorporates dialogue acts and machine reading comprehension techniques to improve accuracy and scalability in task-oriented dialogue systems.

Contribution

It proposes a new model that integrates dialogue acts into state tracking and leverages machine reading comprehension for better slot-value prediction.

Findings

Improved accuracy on the MultiWOZ 2.1 dataset.

Effective prediction of categorical and non-categorical slots.

Demonstrated scalability with dialogue act integration.

Abstract

As an essential component in task-oriented dialogue systems, dialogue state tracking (DST) aims to track human-machine interactions and generate state representations for managing the dialogue. Representations of dialogue states are dependent on the domain ontology and the user's goals. In several task-oriented dialogues with a limited scope of objectives, dialogue states can be represented as a set of slot-value pairs. As the capabilities of dialogue systems expand to support increasing naturalness in communication, incorporating dialogue act processing into dialogue model design becomes essential. The lack of such consideration limits the scalability of dialogue state tracking models for dialogues having specific objectives and ontology. To address this issue, we formulate and incorporate dialogue acts, and leverage recent advances in machine reading comprehension to predict both categorical and non-categorical types of slots for multi-domain dialogue state tracking. Experimental results show that our models can improve the overall accuracy of dialogue state tracking on the MultiWOZ 2.1 dataset, and demonstrate that incorporating dialogue acts can guide dialogue state design for future task-oriented dialogue systems.