AnyTOD: A Programmable Task-Oriented Dialog System

Jeffrey Zhao, Yuan Cao, Raghav Gupta, Harrison Lee, Abhinav Rastogi, Mingqiu Wang, Hagen Soltau, Izhak Shafran, Yonghui Wu


Abstract
We propose AnyTOD, an end-to-end, zero-shot task-oriented dialog (TOD) system capable of zero-shot adaptation onto unseen tasks or domains. We view TOD as a program executed by a language model (LM), where program logic and ontology is provided by a designer as a schema. To enable generalization to unseen schemas and programs without prior training, AnyTOD adopts a neuro-symbolic approach. A neural LM keeps track of events that occur during a conversation, and a symbolic program implementing dialog policy is executed to recommend actions AnyTOD should take. This approach drastically reduces data annotation and model training requirements, addressing the enduring challenge of rapidly adapting a TOD system to unseen tasks and domains. We demonstrate state-of-the-art results on STAR, ABCD and SGD benchmarks. We also demonstrate strong zero-shot transfer ability in low-resource settings, such as zero-shot transfer onto MultiWOZ. In addition, we release STARv2, an updated version of the STAR dataset with richer annotations, for benchmarking zero-shot task transfer for end-to-end TOD models.
Anthology ID:
2023.emnlp-main.1006
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16189–16204
Language:
URL:
https://aclanthology.org/2023.emnlp-main.1006
DOI:
10.18653/v1/2023.emnlp-main.1006
Bibkey:
Cite (ACL):
Jeffrey Zhao, Yuan Cao, Raghav Gupta, Harrison Lee, Abhinav Rastogi, Mingqiu Wang, Hagen Soltau, Izhak Shafran, and Yonghui Wu. 2023. AnyTOD: A Programmable Task-Oriented Dialog System. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 16189–16204, Singapore. Association for Computational Linguistics.
Cite (Informal):
AnyTOD: A Programmable Task-Oriented Dialog System (Zhao et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.1006.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.1006.mp4