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.
@article{arxiv.2203.05797,
title = {Long Time No See! Open-Domain Conversation with Long-Term Persona Memory},
author = {Xinchao Xu and Zhibin Gou and Wenquan Wu and Zheng-Yu Niu and Hua Wu and Haifeng Wang and Shihang Wang},
journal= {arXiv preprint arXiv:2203.05797},
year = {2022}
}
Comments
Accepted by Findings of ACL 2022 (Camera-ready version)