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
  • [41] Augmenting Dialogue Response Generation With Unstructured Textual Knowledge
    Wang, Yanmeng
    Rong, Wenge
    Ouyang, Yuanxin
    Xiong, Zhang
    IEEE ACCESS, 2019, 7 : 34954 - 34963
  • [42] Towards Fewer Hallucinations in Knowledge-Grounded Dialogue Generation via Augmentative and Contrastive Knowledge-Dialogue
    Sun, Bin
    Li, Yitong
    Mi, Fei
    Bie, FanHu
    Li, Yiwei
    Li, Kan
    61ST CONFERENCE OF THE THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL 2023, VOL 2, 2023, : 1741 - 1750
  • [43] Transformer-based Empathetic Response Generation Using Dialogue Situation and Advanced-Level Definition of Empathy
    Wang, Yi-Hsuan
    Hsu, Jia-Hao
    Wu, Chung-Hsien
    Yang, Tsung-Hsien
    2021 12TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2021,
  • [44] Knowledge exchange in the arctic environmental studies: Bridging science and the local community in dialogue
    Stammler-Gossmann, Anna
    POLAR SCIENCE, 2024, 41
  • [45] Adaptive Posterior Knowledge Selection for Improving Knowledge-Grounded Dialogue Generation
    Wang, Weichao
    Gao, Wei
    Feng, Shi
    Chen, Ling
    Wang, Daling
    International Conference on Information and Knowledge Management, Proceedings, 2021, : 1989 - 1998
  • [46] Adaptive Posterior Knowledge Selection for Improving Knowledge-Grounded Dialogue Generation
    Wang, Weichao
    Gao, Wei
    Feng, Shi
    Chen, Ling
    Wang, Daling
    PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021, 2021, : 1989 - 1998
  • [47] BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation
    Yoon, Hee Suk
    Yoon, Eunseop
    Tee, Joshua Tian Jin
    Zhang, Kang
    Heo, Yu-Jung
    Chang, Du-Seong
    Yoo, Chang D.
    COMPUTER VISION - ECCV 2024, PT XXXI, 2025, 15089 : 378 - 396
  • [48] Integrating discourse features and response assessment for advancing empathetic dialogue
    Li, Bobo
    Fei, Hao
    Su, Fangfang
    Li, Fei
    Ji, Donghong
    INFORMATION PROCESSING & MANAGEMENT, 2024, 61 (05)
  • [49] Empathetic Response Generation for Distress Support
    Yeh, Chun-Hung
    Welivita, Anuradha
    Pu, Pearl
    24TH MEETING OF THE SPECIAL INTEREST GROUP ON DISCOURSE AND DIALOGUE, SIGDIAL 2023, 2023, : 632 - 644
  • [50] Knowledge grounded medical dialogue generation using augmented graphs
    Varshney, Deeksha
    Zafar, Aizan
    Behera, Niranshu Kumar
    Ekbal, Asif
    SCIENTIFIC REPORTS, 2023, 13 (01)