Domain-Aware Dialogue State Tracker for Multi-Domain Dialogue Systems
This addresses scalability issues for large-scale conversational agents needing to interface with increasing services, though it appears incremental as it builds on existing pretrained models.
The paper tackles the problem of dialogue state tracking in task-oriented systems being limited by predefined ontologies, proposing a domain-aware tracker that predicts for dynamic service schemas and achieves effective learning of semantic relations by integrating with BERT.
In task-oriented dialogue systems the dialogue state tracker (DST) component is responsible for predicting the state of the dialogue based on the dialogue history. Current DST approaches rely on a predefined domain ontology, a fact that limits their effective usage for large scale conversational agents, where the DST constantly needs to be interfaced with ever-increasing services and APIs. Focused towards overcoming this drawback, we propose a domain-aware dialogue state tracker, that is completely data-driven and it is modeled to predict for dynamic service schemas. The proposed model utilizes domain and slot information to extract both domain and slot specific representations for a given dialogue, and then uses such representations to predict the values of the corresponding slot. Integrating this mechanism with a pretrained language model (i.e. BERT), our approach can effectively learn semantic relations.