Dialogue State Induction Using Neural Latent Variable Models
This addresses the challenge of scaling dialogue systems across diverse domains for customer service by reducing reliance on manual labeling, though it is incremental as it builds on existing neural methods.
The authors tackled the problem of costly manual labeling for dialogue state modules by proposing dialogue state induction using neural latent variable models to automatically mine states from unlabeled customer service dialogues, resulting in effective slot discovery and improved performance in a state-of-the-art dialogue system.
Dialogue state modules are a useful component in a task-oriented dialogue system. Traditional methods find dialogue states by manually labeling training corpora, upon which neural models are trained. However, the labeling process can be costly, slow, error-prone, and more importantly, cannot cover the vast range of domains in real-world dialogues for customer service. We propose the task of dialogue state induction, building two neural latent variable models that mine dialogue states automatically from unlabeled customer service dialogue records. Results show that the models can effectively find meaningful slots. In addition, equipped with induced dialogue states, a state-of-the-art dialogue system gives better performance compared with not using a dialogue state module.