Unsupervised Slot Schema Induction for Task-oriented Dialog

Anonymous

Paper Link: https://openreview.net/forum?id=5moYSLDDnop

Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)

Abstract: 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, laborious, iterative, and slow, especially when the schema is complicated. To alleviate this expensive and time consuming process, we propose an unsupervised approach for slot schema induction from unlabeled dialog corpora. Leveraging in-domain language models and unsupervised parsing structures, our data-driven approach extracts candidate slots without constraints, followed by coarse-to-fine clustering to induce slot types. We compare our method against several strong supervised baselines, and show significant performance improvement in slot schema induction on MultiWoz and SGD datasets. We also demonstrate the effectiveness of induced schemas on downstream applications including dialog state tracking and response generation.

Presentation Mode: This paper will be presented in person in Seattle

Copyright Consent Signature (type Name Or NA If Not Transferrable): Dian Yu

Copyright Consent Name And Address: University of California, Davis 1 Shields Ave, Davis, CA 95616; Google 1600 Amphitheatre Parkway Mountain View, CA 94043