Domain-Aware Dialogue State Tracker for Multi-Domain Dialogue Systems

In task-oriented dialogue systems the dialogue state tracker component (DST) is responsible for predicting the current state of the dialogue based on the dialogue history and the user utterance. 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, including zero-shot domains. Unlike approaches that propose separate models for prediction of intents, requested slots, slot status, categorical slots and non-categorical slots, we propose a single model in an end-to-end architecture. The proposed model utilizes domain and slot information to extract both domain and slot specific representations from a given dialogue, and then uses such representations to predict the values of the corresponding slot in a given domain. Integrating this mechanism with pretrained language models, our approach can effectively learn semantic relations and effectively perform transfer learning between domains or zero-shot tracking for domains not present in training.