Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering
This addresses the challenge of generalizing to unseen domains, slots, and values in conversational AI systems, representing a strong specific gain rather than a foundational breakthrough.
The paper tackles the problem of multi-domain dialogue state tracking by modeling it as a question answering task, achieving a 5.80% and 12.21% relative improvement over the state-of-the-art on MultiWOZ 2.0 and 2.1 datasets, respectively.
Multi-domain dialogue state tracking (DST) is a critical component for conversational AI systems. The domain ontology (i.e., specification of domains, slots, and values) of a conversational AI system is generally incomplete, making the capability for DST models to generalize to new slots, values, and domains during inference imperative. In this paper, we propose to model multi-domain DST as a question answering problem, referred to as Dialogue State Tracking via Question Answering (DSTQA). Within DSTQA, each turn generates a question asking for the value of a (domain, slot) pair, thus making it naturally extensible to unseen domains, slots, and values. Additionally, we use a dynamically-evolving knowledge graph to explicitly learn relationships between (domain, slot) pairs. Our model has a 5.80% and 12.21% relative improvement over the current state-of-the-art model on MultiWOZ 2.0 and MultiWOZ 2.1 datasets, respectively. Additionally, our model consistently outperforms the state-of-the-art model in domain adaptation settings. (Code is released at https://github.com/alexa/dstqa )