PARL: A Dialog System Framework with Prompts as Actions for Reinforcement Learning

Tao Xiang, Yangzhe Li, Monika Wintergerst, Ana Pecini, Dominika Młynarczyk, Georg Groh

2023

Abstract

The performance of most current open-domain dialog systems is limited by the (training) dialog corpora due to either generation-based or retrieval-based learning patterns. To circumvent this limitation, we propose PARL, an open-domain dialog system framework using Prompts as Actions for Reinforcement Learning. This framework requires a (fixed) open-domain dialog system as the backbone and trains a behavior policy using reinforcement learning to guide the backbone system to respond appropriately with respect to a given conversation. The action space is defined as a finite set of behaviors in the form of natural language prompts. Preliminary results show that with the guidance of the behavior policy, the backbone system could generate more engaging and empathetic responses.

Paper Citation

in Harvard Style

Xiang T., Li Y., Wintergerst M., Pecini A., Młynarczyk D. and Groh G. (2023). PARL: A Dialog System Framework with Prompts as Actions for Reinforcement Learning. In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, ISBN 978-989-758-623-1, pages 633-640. DOI: 10.5220/0011725200003393

in Bibtex Style

@conference{icaart23,
author={Tao Xiang and Yangzhe Li and Monika Wintergerst and Ana Pecini and Dominika Młynarczyk and Georg Groh},
title={PARL: A Dialog System Framework with Prompts as Actions for Reinforcement Learning},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2023},
pages={633-640},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011725200003393},
isbn={978-989-758-623-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,
TI - PARL: A Dialog System Framework with Prompts as Actions for Reinforcement Learning
SN - 978-989-758-623-1
AU - Xiang T.
AU - Li Y.
AU - Wintergerst M.
AU - Pecini A.
AU - Młynarczyk D.
AU - Groh G.
PY - 2023
SP - 633
EP - 640
DO - 10.5220/0011725200003393