Abstract
The design of dialogue flows is a critical but time-consuming task when developing task-oriented dialogue (TOD) systems. We propose an approach for the unsupervised discovery of flows from dialogue history, thus making the process applicable to any domain for which such an history is available. Briefly, utterances are represented in a vector space and clustered according to their semantic similarity. Clusters, which can be seen as dialogue states, are then used as the vertices of a transition graph for representing the flows visually. We present concrete examples of flows, discovered from MultiWOZ, a public TOD dataset. We further elaborate on their significance and relevance for the underlying conversations and introduce an automatic validation metric for their assessment. Experimental results demonstrate the potential of the proposed approach for extracting meaningful flows from task-oriented conversations.
Abstract (translated)
对话流设计的有效性是一个关键但耗时费力的任务,尤其是在开发面向任务的对话系统(TOD)时。我们提出了一个无监督地从对话历史中发现流的方法,从而使该过程适用于任何可以获得这种历史的领域。简而言之,的话语用向量空间来表示,并根据其语义相似性进行聚类。然后,这些聚类被用作表示流 visually 的顶点,我们可以从MultiWOZ等公共TOD数据集中发现这些流。我们进一步详细介绍了它们在对话背后的意义和重要性,并引入了一个自动验证指标来评估它们的准确性。实验结果表明,所提出的方案具有从面向任务对话中提取有意义的流的潜力。
URL
https://arxiv.org/abs/2405.01403