Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems

Hsien-chin Lin, Nurul Lubis, Songbo Hu, Carel van Niekerk, Christian Geishauser, Michael Heck, Shutong Feng, Milica Gasic


Abstract
Dialogue policy optimisation via reinforcement learning requires a large number of training interactions, which makes learning with real users time consuming and expensive. Many set-ups therefore rely on a user simulator instead of humans. These user simulators have their own problems. While hand-coded, rule-based user simulators have been shown to be sufficient in small, simple domains, for complex domains the number of rules quickly becomes intractable. State-of-the-art data-driven user simulators, on the other hand, are still domain-dependent. This means that adaptation to each new domain requires redesigning and retraining. In this work, we propose a domain-independent transformer-based user simulator (TUS). The structure of TUS is not tied to a specific domain, enabling domain generalization and the learning of cross-domain user behaviour from data. We compare TUS with the state-of-the-art using automatic as well as human evaluations. TUS can compete with rule-based user simulators on pre-defined domains and is able to generalize to unseen domains in a zero-shot fashion.
Anthology ID:
2021.sigdial-1.47
Volume:
Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
July
Year:
2021
Address:
Singapore and Online
Editors:
Haizhou Li, Gina-Anne Levow, Zhou Yu, Chitralekha Gupta, Berrak Sisman, Siqi Cai, David Vandyke, Nina Dethlefs, Yan Wu, Junyi Jessy Li
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
445–456
Language:
URL:
https://aclanthology.org/2021.sigdial-1.47
DOI:
10.18653/v1/2021.sigdial-1.47
Bibkey:
Cite (ACL):
Hsien-chin Lin, Nurul Lubis, Songbo Hu, Carel van Niekerk, Christian Geishauser, Michael Heck, Shutong Feng, and Milica Gasic. 2021. Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 445–456, Singapore and Online. Association for Computational Linguistics.
Cite (Informal):
Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems (Lin et al., SIGDIAL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.sigdial-1.47.pdf
Video:
 https://www.youtube.com/watch?v=WAWFDEk1yvc
Data
MultiWOZ