论文标题
对话状态归纳使用神经潜在变量模型
Dialogue State Induction Using Neural Latent Variable Models
论文作者
论文摘要
对话状态模块是面向任务的对话系统中的有用组件。传统方法通过手动标记培训语料库来查找对话状态，并在其上培训了神经模型。但是，标签过程可能是昂贵，缓慢，容易出错的，更重要的是，在现实世界中的客户服务对话中不能涵盖广泛的域。我们提出了对话状态归纳的任务，建立了两种神经潜在变量模型，这些模型会自动从未标记的客户服务对话记录中自动指出。结果表明，模型可以有效地找到有意义的插槽。此外，配备了诱发对话状态，与不使用对话状态模块相比，最新的对话系统可提供更好的性能。
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.
