Improving Dialog Systems for Negotiation with Personality Modeling

Runzhe Yang, Jingxiao Chen, Karthik Narasimhan


Abstract
In this paper, we explore the ability to model and infer personality types of opponents, predict their responses, and use this information to adapt a dialog agent’s high-level strategy in negotiation tasks. Inspired by the idea of incorporating a theory of mind (ToM) into machines, we introduce a probabilistic formulation to encapsulate the opponent’s personality type during both learning and inference. We test our approach on the CraigslistBargain dataset (He et al. 2018) and show that our method using ToM inference achieves a 20% higher dialog agreement rate compared to baselines on a mixed population of opponents. We also demonstrate that our model displays diverse negotiation behavior with different types of opponents.
Anthology ID:
2021.acl-long.56
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
681–693
Language:
URL:
https://aclanthology.org/2021.acl-long.56
DOI:
10.18653/v1/2021.acl-long.56
Bibkey:
Cite (ACL):
Runzhe Yang, Jingxiao Chen, and Karthik Narasimhan. 2021. Improving Dialog Systems for Negotiation with Personality Modeling. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 681–693, Online. Association for Computational Linguistics.
Cite (Informal):
Improving Dialog Systems for Negotiation with Personality Modeling (Yang et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.acl-long.56.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2021.acl-long.56.mp4
Code
 princeton-nlp/NegotiationToM