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
  • [31] Empathetic Robot With Transformer-Based Dialogue Agent
    Xie, Baijun
    Park, Chung Hyuk
    2021 18TH INTERNATIONAL CONFERENCE ON UBIQUITOUS ROBOTS (UR), 2021, : 290 - 295
  • [32] Dynamically retrieving knowledge via query generation for informative dialogue generation
    Hu, Zhongtian
    Wang, Lifang
    Chen, Yangqi
    Liu, Yushuang
    Li, Ronghan
    Zhao, Meng
    Lu, Xinyu
    Jiang, Zejun
    NEUROCOMPUTING, 2024, 569
  • [33] Combining Curriculum Learning and Knowledge Distillation for Dialogue Generation
    Zhu, Qingqing
    Chen, Xiuying
    Wu, Pengfei
    Liu, JunFei
    Zhao, Dongyan
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2021, 2021, : 1284 - 1295
  • [34] Exploring implicit persona knowledge for personalized dialogue generation
    Fuyong Xu
    Zhaoxin Ding
    Zhenfang Zhu
    Peiyu Liu
    The Journal of Supercomputing, 2023, 79 : 14545 - 14570
  • [35] Knowledge Augmented Dialogue Generation with Divergent Facts Selection
    Jiang, Bin
    Yang, Jingxu
    Yang, Chao
    Zhou, Wanyue
    Pang, Liang
    Zhou, Xiaokang
    KNOWLEDGE-BASED SYSTEMS, 2020, 210
  • [36] Automatic knowledge generation for a persuasion dialogue system with enthymemes
    Leiva, Diego S. Orbe
    Gottifredi, Sebastian
    Garcia, Alejandro J.
    INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2023, 160
  • [37] Exploring implicit persona knowledge for personalized dialogue generation
    Xu, Fuyong
    Ding, Zhaoxin
    Zhu, Zhenfang
    Liu, Peiyu
    JOURNAL OF SUPERCOMPUTING, 2023, 79 (13): : 14545 - 14570
  • [38] Insert Commonsense Knowledge Through Semantics for Dialogue Generation
    Hou, Siqi
    Song, Dandan
    Wu, Zhijing
    Guo, Xiechao
    Yang, Ziyi
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT II, KSEM 2024, 2024, 14885 : 305 - 317
  • [39] Multiple Knowledge Syncretic Transformer for Natural Dialogue Generation
    Zhao, Xiangyu
    Wang, Longbiao
    He, Ruifang
    Yang, Ting
    Chang, Jinxin
    Wang, Ruifang
    WEB CONFERENCE 2020: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2020), 2020, : 752 - 762
  • [40] Improving Dialogue Generation with Commonsense Knowledge Fusion and Selection
    Fu, Dongjun
    Zhang, Chunhong
    Yu, Jibin
    Sun, Qi
    Zhan, Zhiqiang
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT I, 2022, 13368 : 93 - 108