Schema Graph-Guided Prompt for Multi-Domain Dialogue State Tracking
This work addresses the challenge of adapting dialogue state tracking to specific domains for task-oriented dialogue systems, representing an incremental improvement over existing methods.
The paper tackles the problem of limited performance of general pre-trained language models in multi-domain dialogue state tracking by proposing a graph-based framework that incorporates domain-specific schema via a graph neural network, resulting in outperforming other approaches with similar or fewer parameters.
Tracking dialogue states is an essential topic in task-oriented dialogue systems, which involve filling in the necessary information in pre-defined slots corresponding to a schema. While general pre-trained language models have been shown effective in slot-filling, their performance is limited when applied to specific domains. We propose a graph-based framework that learns domain-specific prompts by incorporating the dialogue schema. Specifically, we embed domain-specific schema encoded by a graph neural network into the pre-trained language model, which allows for relations in the schema to guide the model for better adaptation to the specific domain. Our experiments demonstrate that the proposed graph-based method outperforms other multi-domain DST approaches while using similar or fewer trainable parameters. We also conduct a comprehensive study of schema graph architectures, parameter usage, and module ablation that demonstrate the effectiveness of our model on multi-domain dialogue state tracking.