Show, Don’t Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue
Raghav Gupta, Harrison Lee, Jeffrey Zhao, Yuan Cao, Abhinav Rastogi, Yonghui Wu
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.
BibTeX
@inproceedings{gupta-etal-2022-show,
title = "Show, Don{'}t Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue",
author = "Gupta, Raghav and
Lee, Harrison and
Zhao, Jeffrey and
Cao, Yuan and
Rastogi, Abhinav and
Wu, Yonghui",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.336/",
doi = "10.18653/v1/2022.naacl-main.336",
pages = "4541--4549"
}