Long Time No See! Open-Domain Conversation with Long-Term Persona Memory

Xinchao Xu, Zhibin Gou, Wenquan Wu, Zheng-Yu Niu, Hua Wu, Haifeng Wang, Shihang Wang

Abstract
Most of the open-domain dialogue models tend to perform poorly in the setting of long-term human-bot conversations. The possible reason is that they lack the capability of understanding and memorizing long-term dialogue history information. To address this issue, we present a novel task of Long-term Memory Conversation (LeMon) and then build a new dialogue dataset DuLeMon and a dialogue generation framework with Long-Term Memory (LTM) mechanism (called PLATO-LTM). This LTM mechanism enables our system to accurately extract and continuously update long-term persona memory without requiring multiple-session dialogue datasets for model training. To our knowledge, this is the first attempt to conduct real-time dynamic management of persona information of both parties, including the user and the bot. Results on DuLeMon indicate that PLATO-LTM can significantly outperform baselines in terms of long-term dialogue consistency, leading to better dialogue engagingness.
Anthology ID:
2022.findings-acl.207
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2639–2650
Language:
URL:
https://aclanthology.org/2022.findings-acl.207
DOI:
10.18653/v1/2022.findings-acl.207
Bibkey:
Cite (ACL):
Xinchao Xu, Zhibin Gou, Wenquan Wu, Zheng-Yu Niu, Hua Wu, Haifeng Wang, and Shihang Wang. 2022. Long Time No See! Open-Domain Conversation with Long-Term Persona Memory. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2639–2650, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Long Time No See! Open-Domain Conversation with Long-Term Persona Memory (Xu et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2022.findings-acl.207.pdf
Code
 PaddlePaddle/Research
Data
DuLeMon
PDF Search Code