GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers
Hsien-chin Lin, Christian Geishauser, Shutong Feng, Nurul Lubis, Carel van Niekerk, Michael Heck, Milica Gasic
Abstract
User simulators (USs) are commonly used to train task-oriented dialogue systems via reinforcement learning. The interactions often take place on semantic level for efficiency, but there is still a gap from semantic actions to natural language, which causes a mismatch between training and deployment environment. Incorporating a natural language generation (NLG) module with USs during training can partly deal with this problem. However, since the policy and NLG of USs are optimised separately, these simulated user utterances may not be natural enough in a given context. In this work, we propose a generative transformer-based user simulator (GenTUS). GenTUS consists of an encoder-decoder structure, which means it can optimise both the user policy and natural language generation jointly. GenTUS generates both semantic actions and natural language utterances, preserving interpretability and enhancing language variation. In addition, by representing the inputs and outputs as word sequences and by using a large pre-trained language model we can achieve generalisability in feature representation. We evaluate GenTUS with automatic metrics and human evaluation. Our results show that GenTUS generates more natural language and is able to transfer to an unseen ontology in a zero-shot fashion. In addition, its behaviour can be further shaped with reinforcement learning opening the door to training specialised user simulators.- Anthology ID:
- 2022.sigdial-1.28
- Volume:
- Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue
- Month:
- September
- Year:
- 2022
- Address:
- Edinburgh, UK
- Editors:
- Oliver Lemon, Dilek Hakkani-Tur, Junyi Jessy Li, Arash Ashrafzadeh, Daniel Hernández Garcia, Malihe Alikhani, David Vandyke, Ondřej Dušek
- Venue:
- SIGDIAL
- SIG:
- SIGDIAL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 270–282
- Language:
- URL:
- https://aclanthology.org/2022.sigdial-1.28
- DOI:
- 10.18653/v1/2022.sigdial-1.28
- Cite (ACL):
- Hsien-chin Lin, Christian Geishauser, Shutong Feng, Nurul Lubis, Carel van Niekerk, Michael Heck, and Milica Gasic. 2022. GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 270–282, Edinburgh, UK. Association for Computational Linguistics.
- Cite (Informal):
- GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers (Lin et al., SIGDIAL 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.sigdial-1.28.pdf
- Data
- MultiWOZ