论文标题
火星：对端到端任务对话的对比度学习进行建模上下文和状态表示。
Mars: Modeling Context & State Representations with Contrastive Learning for End-to-End Task-Oriented Dialog
论文作者
论文摘要
传统的端到端任务对话框系统首先将对话框上下文转换为信念状态和动作状态，然后再产生系统响应。系统响应性能受到信念状态和行动状态的质量的显着影响。我们首先探索哪种对话上下文表示有益于提高信仰状态和行动状态的质量，从而进一步提高了产生的响应质量。为了解决我们的探索，我们提出了MARS，这是一种端到端的以任务为导向的对话系统，具有两种对比学习策略，以模拟对话框上下文与信念/行动状态表示之间的关系。经验结果显示对话上下文表示，与语义状态表示更有不同，更有利于多转变为以任务为导向的对话框。此外，我们提议的火星在Multiwoz 2.0，Camrest676和Crosswoz上实现了最先进的表现。
Traditional end-to-end task-oriented dialog systems first convert dialog context into belief state and action state before generating the system response. The system response performance is significantly affected by the quality of the belief state and action state. We first explore what dialog context representation is beneficial to improving the quality of the belief state and action state, which further enhances the generated response quality. To tackle our exploration, we propose Mars, an end-to-end task-oriented dialog system with two contrastive learning strategies to model the relationship between dialog context and belief/action state representations. Empirical results show dialog context representations, which are more different from semantic state representations, are more conducive to multi-turn task-oriented dialog. Moreover, our proposed Mars achieves state-of-the-art performance on the MultiWOZ 2.0, CamRest676, and CrossWOZ.
