Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking
This work addresses scalability issues in dialogue state tracking for task-oriented dialogue systems, which is incremental as it builds on existing methods by adding dialogue act processing.
The paper tackled the problem of dialogue state tracking in multi-domain task-oriented dialogues by incorporating dialogue act processing to improve scalability and accuracy, achieving improved overall accuracy on the MultiWOZ 2.1 dataset.
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.