Self-supervised Schema Induction for Task-oriented Dialog
Hand-crafted schemas describing how to collect and annotate dialog corpora are a prerequisite towards building task-oriented dialog systems. In practical applications, manually designing schemas can be error-prone, laborious, iterative, and slow, especially when the schema is complicated. To automate this process, we propose a self-supervised approach for schema induction from unlabeled dialog corpora. Our approach utilizes representations provided by in-domain language models constrained on unsupervised structures, followed by multi-step coarse-to-fine clustering. We compare our method against several strong supervised baselines, and show significant performance improvement in schema induction on MultiWoz and SGD datasets. We also demonstrate the effectiveness of induced schemas on downstream tasks including dialog state tracking and response generation.
Code (0)
등록된 구현이 없습니다.
Tasks
Clusteringdialog state trackingResponse GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Unsupervised Slot Schema Induction for Task-oriented Dialog
Carefully-designed schemas describing how to collect and annotate dialog corpora are a prerequisite towards building task-oriented dialog systems. In practical applications, manually designing schemas can be error-prone,…
Clusteringdialog state trackingResponse GenerationUnsupervised Slot Schema Induction for Task-oriented Dialog
Carefully-designed schemas describing how to collect and annotate dialog corpora are a prerequisite towards building task-oriented dialog systems. In practical applications, manually designing schemas can be error-prone,…
dialog state trackingResponse GenerationAnalysis of Utterance Embeddings and Clustering Methods Related to Intent Induction for Task-Oriented Dialogue
The focus of this work is to investigate unsupervised approaches to overcome quintessential challenges in designing task-oriented dialog schema: assigning intent labels to each dialog turn (intent clustering) and generat…
ClusteringTransforming Slot Schema Induction with Generative Dialogue State Inference
The challenge of defining a slot schema to represent the state of a task-oriented dialogue system is addressed by Slot Schema Induction (SSI), which aims to automatically induce slots from unlabeled dialogue data. Wherea…
Intent Induction from Conversations for Task-Oriented Dialogue Track at DSTC 11
With increasing demand for and adoption of virtual assistants, recent work has investigated ways to accelerate bot schema design through the automatic induction of intents or the induction of slots and dialogue states. H…