论文标题
与插槽集群的以任务为导向的对话中的结构提取
Structure Extraction in Task-Oriented Dialogues with Slot Clustering
论文作者
论文摘要
从对话数据中提取结构信息可以帮助我们更好地了解用户和系统行为。在面向任务的对话中，对话结构通常被视为对话态之间的过渡图。但是，注释对话指示手动昂贵且耗时。在本文中，我们提出了一种简单而有效的方法，用于以任务为导向的对话中提取结构。我们首先使用预训练的模型检测和群集可能的插槽令牌，以近似目标域的对话本体。然后，我们跟踪每个已识别的令牌组的状态并得出状态过渡结构。经验结果表明，我们的方法在对话结构提取的范围内超过了无监督的基线模型。此外，我们表明，基于提取结构的数据增强丰富了训练数据的表面形式，并可以在对话响应产生中显着提高性能。
Extracting structure information from dialogue data can help us better understand user and system behaviors. In task-oriented dialogues, dialogue structure has often been considered as transition graphs among dialogue states. However, annotating dialogue states manually is expensive and time-consuming. In this paper, we propose a simple yet effective approach for structure extraction in task-oriented dialogues. We first detect and cluster possible slot tokens with a pre-trained model to approximate dialogue ontology for a target domain. Then we track the status of each identified token group and derive a state transition structure. Empirical results show that our approach outperforms unsupervised baseline models by far in dialogue structure extraction. In addition, we show that data augmentation based on extracted structures enriches the surface formats of training data and can achieve a significant performance boost in dialogue response generation.
