Knowledge Bridging for Empathetic Dialogue Generation

被引:0
|
作者
Li, Qintong [1 ,3 ]
Li, Piji [2 ]
Ren, Zhaochun [1 ]
Ren, Pengjie [1 ]
Chen, Zhumin [1 ]
机构
[1] Shandong Univ, Sch Comp Sci & Technol, Qingdao, Peoples R China
[2] Tencent AI Lab, Shenzhen, Peoples R China
[3] Univ Hong Kong, Dept Comp Sci, Hong Kong, Peoples R China
基金
国家重点研发计划;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Lack of external knowledge makes empathetic dialogue systems difficult to perceive implicit emotions and learn emotional interactions from limited dialogue history. To address the above problems, we propose to leverage external knowledge, including commonsense knowledge and emotional lexical knowledge, to explicitly understand and express emotions in empathetic dialogue generation. We first enrich the dialogue history by jointly interacting with external knowledge and construct an emotional context graph. Then we learn emotional context representations from the knowledge-enriched emotional context graph and distill emotional signals, which are the prerequisites to predicate emotions expressed in responses. Finally, to generate the empathetic response, we propose an emotional cross-attention mechanism to learn the emotional dependencies from the emotional context graph. Extensive experiments conducted on a benchmark dataset verify the effectiveness of the proposed method. In addition, we find the performance of our method can be further improved by integrating with a pre-trained model that works orthogonally.
引用
收藏
页码:10993 / 11001
页数:9
相关论文
共 50 条
  • [1] KnowDT: Empathetic dialogue generation with knowledge enhanced dependency tree
    Liu, Yuan
    Han, Donghong
    Wu, Gang
    Qiao, Baiyou
    APPLIED INTELLIGENCE, 2024, 54 (17-18) : 8059 - 8072
  • [2] Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge
    Cai, Hua
    Shen, Xuli
    Xu, Qing
    Shen, Weilin
    Wang, Xiaomei
    Ge, Weifeng
    Zheng, Xiaoqing
    Xue, Xiangyang
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2023), 2023, : 7858 - 7873
  • [3] IECCK: integrating emotion cause and common knowledge for empathetic dialogue generation
    Cao, Xiaopeng
    Meng, Ting
    Bi, Xiaoxia
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2024,
  • [4] Multi-Level Knowledge-Enhanced Prompting for Empathetic Dialogue Generation
    Gu, Ziyin
    Zhu, Qingmeng
    He, Hao
    Yu, Zhipeng
    Lan, Tianxing
    Yuan, Shuo
    PROCEEDINGS OF THE 2024 27 TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN, CSCWD 2024, 2024, : 3170 - 3175
  • [5] Improving Empathetic Dialogue Generation with Semantics Decoupling
    Pan, Rui
    Zou, Minghui
    Zhang, Sai
    Yu, Yongxin
    Feng, Zhiyong
    PROCEEDINGS OF THE 11TH INTERNATIONAL JOINT CONFERENCE ON KNOWLEDGE GRAPHS, IJCKG 2022, 2022, : 55 - 63
  • [6] Implicit and Explicit Emotion Enhanced Empathetic Dialogue Generation
    Zhu, Qingmeng
    Li, Chen
    He, Hao
    Song, Hetian
    Gu, Ziyin
    Ying, Wenjing
    2022 IEEE 34TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI, 2022, : 1396 - 1404
  • [7] Conditional Adversarial Learning for Empathetic Dialogue Response Generation
    Su, Ming-Hsiang
    Wu, Chung-Hsien
    Liao, Chia-Yu
    APSIPA TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING, 2023, 12 (01)
  • [8] Empathetic Dialogue Generation via Sentiment and Support Strategy
    Zhu, Zhenfang
    Li, Jiaxin
    Xu, Fuyong
    Liu, Peiyu
    Zhang, Guangyuan
    Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology, 2024, 46 (08): : 3382 - 3389
  • [9] Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation
    Chen, Xiuyi
    Meng, Fandong
    Li, Peng
    Chen, Feilong
    Xu, Shuang
    Xu, Bo
    Zhou, Jie
    PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 3426 - 3437
  • [10] Multi-perspective empathy modeling for empathetic dialogue generation
    Qiao, Baiyou
    Zhang, Yuekai
    Gao, Pan
    Li, Xinchi
    Wang, Shuo
    Han, Donghong
    KNOWLEDGE-BASED SYSTEMS, 2025, 314