跳到主要导航 跳到搜索 跳到主要内容

Improving Personality Consistency in Conversation by Persona Extending

  • Yifan Liu
  • , Wei Wei*
  • , Jiayi Liu
  • , Xianling Mao
  • , Rui Fang
  • , Dangyang Chen
  • *此作品的通讯作者
  • Huazhong University of Science and Technology
  • Alibaba Group Holding Ltd.
  • Ltd

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Endowing chatbots with a consistent personality plays a vital role for agents to deliver human-like interactions. However, existing personalized approaches commonly generate responses in light of static predefined personas depicted with textual description, which may severely restrict the interactivity of human and the chatbot, especially when the agent needs to answer the query excluded in the predefined personas, which is so-called out-of-predefined persona problem (named OOP for simplicity). To alleviate the problem, in this paper we propose a novel retrieval-to-prediction paradigm consisting of two subcomponents, namely, (1) Persona Retrieval Model (PRM), it retrieves a persona from a global collection based on a Natural Language Inference (NLI) model, the inferred persona is consistent with the predefined personas; and (2) Posterior-scored Transformer (PS-Transformer), it adopts a persona posterior distribution that further considers the actual personas used in the ground response, maximally mitigating the gap between training and inferring. Furthermore, we present a dataset called IT-ConvAI2 that first highlights the OOP problem in personalized dialogue. Extensive experiments on both IT-ConvAI2 and ConvAI2 demonstrate that our proposed model yields considerable improvements in both automatic metrics and human evaluations.

源语言英语
主期刊名CIKM 2022 - Proceedings of the 31st ACM International Conference on Information and Knowledge Management
出版商Association for Computing Machinery
1350-1359
页数10
ISBN(电子版)9781450392365
DOI
出版状态已出版 - 17 10月 2022
活动31st ACM International Conference on Information and Knowledge Management, CIKM 2022 - Atlanta, 美国
期限: 17 10月 202221 10月 2022

丛书

姓名International Conference on Information and Knowledge Management, Proceedings
ISSN(印刷版)2155-0751

会议

会议31st ACM International Conference on Information and Knowledge Management, CIKM 2022
国家/地区美国
Atlanta
时期17/10/2221/10/22

学术指纹

探究 'Improving Personality Consistency in Conversation by Persona Extending' 的科研主题。它们共同构成独一无二的学术指纹。

引用此