Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue

Anonymous

Paper Link: https://openreview.net/forum?id=RNI5LO-axuw

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

Abstract: Building universal dialogue systems that operate across multiple domains/APIs and generalize to new ones with minimal overhead is a critical challenge. Recent works have leveraged natural language descriptions of schema elements to enable such systems; however, descriptions only indirectly convey schema semantics. In this work, we propose Show, Don't Tell, which prompts seq2seq models with a labeled example dialogue to show the semantics of schema elements rather than tell the model through descriptions. While requiring similar effort from service developers as generating descriptions, we show that using short examples as schema representations with large language models results in state-of-the-art performance on two popular dialogue state tracking benchmarks designed to measure zero-shot generalization - the Schema-Guided Dialogue dataset and the MultiWOZ leave-one-out benchmark.

Copyright Consent Signature (type Name Or NA If Not Transferrable): Raghav Gupta

Copyright Consent Name And Address: Google, 1600 Amphitheatre Parkway, Mountain View CA 94040, United States

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