Unsupervised Flow Discovery from Task-oriented Dialogues

arXiv:2405.01403v1 Announce Type: new
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 …

abstract arxiv cs.ai cs.cl design dialogue discovery domain flow history making process systems type unsupervised