Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing
This addresses the scalability challenge in dialogue systems for multi-domain applications, representing a strong specific gain rather than a foundational breakthrough.
The paper tackles the problem of scaling dialogue belief tracking to multi-domain settings by introducing a novel approach that leverages semantic similarity between utterances and ontology terms to share information across domains. The model outperforms existing state-of-the-art models in single-domain tasks and is evaluated on a dataset ten times larger than previous corpora.
Robust dialogue belief tracking is a key component in maintaining good quality dialogue systems. The tasks that dialogue systems are trying to solve are becoming increasingly complex, requiring scalability to multi domain, semantically rich dialogues. However, most current approaches have difficulty scaling up with domains because of the dependency of the model parameters on the dialogue ontology. In this paper, a novel approach is introduced that fully utilizes semantic similarity between dialogue utterances and the ontology terms, allowing the information to be shared across domains. The evaluation is performed on a recently collected multi-domain dialogues dataset, one order of magnitude larger than currently available corpora. Our model demonstrates great capability in handling multi-domain dialogues, simultaneously outperforming existing state-of-the-art models in single-domain dialogue tracking tasks.