Towards Socially Intelligent Agents with Mental State Transition and Human Value

Liang Qiu, Yizhou Zhao, Yuan Liang, Pan Lu, Weiyan Shi, Zhou Yu, Song-Chun Zhu


Abstract
Building a socially intelligent agent involves many challenges. One of which is to track the agent’s mental state transition and teach the agent to make decisions guided by its value like a human. Towards this end, we propose to incorporate mental state simulation and value modeling into dialogue agents. First, we build a hybrid mental state parser that extracts information from both the dialogue and event observations and maintains a graphical representation of the agent’s mind; Meanwhile, the transformer-based value model learns human preferences from the human value dataset, ValueNet. Empirical results show that the proposed model attains state-of-the-art performance on the dialogue/action/emotion prediction task in the fantasy text-adventure game dataset, LIGHT. We also show example cases to demonstrate: (i) how the proposed mental state parser can assist the agent’s decision by grounding on the context like locations and objects, and (ii) how the value model can help the agent make decisions based on its personal priorities.
Anthology ID:
2022.sigdial-1.16
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:
146–158
Language:
URL:
https://aclanthology.org/2022.sigdial-1.16
DOI:
10.18653/v1/2022.sigdial-1.16
Bibkey:
Cite (ACL):
Liang Qiu, Yizhou Zhao, Yuan Liang, Pan Lu, Weiyan Shi, Zhou Yu, and Song-Chun Zhu. 2022. Towards Socially Intelligent Agents with Mental State Transition and Human Value. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 146–158, Edinburgh, UK. Association for Computational Linguistics.
Cite (Informal):
Towards Socially Intelligent Agents with Mental State Transition and Human Value (Qiu et al., SIGDIAL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.sigdial-1.16.pdf
Video:
 https://youtu.be/Oo2gsoHc6YI