About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Collaborative Computing: Networking, Applications and Worksharing. 19th EAI International Conference, CollaborateCom 2023, Corfu Island, Greece, October 4-6, 2023, Proceedings, Part II

Research Article

ECCRG: A Emotion- and Content-Controllable Response Generation Model

Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-031-54528-3_7,
        author={Hui Chen and Bo Wang and Ke Yang and Yi Song},
        title={ECCRG: A Emotion- and Content-Controllable Response Generation Model},
        proceedings={Collaborative Computing: Networking, Applications and Worksharing. 19th EAI International Conference, CollaborateCom 2023, Corfu Island, Greece, October 4-6, 2023, Proceedings, Part II},
        proceedings_a={COLLABORATECOM PART 2},
        year={2024},
        month={2},
        keywords={Dialogue systems Emotional response generation Controllable text generation},
        doi={10.1007/978-3-031-54528-3_7}
    }
    
  • Hui Chen
    Bo Wang
    Ke Yang
    Yi Song
    Year: 2024
    ECCRG: A Emotion- and Content-Controllable Response Generation Model
    COLLABORATECOM PART 2
    Springer
    DOI: 10.1007/978-3-031-54528-3_7
Hui Chen1, Bo Wang2,*, Ke Yang1, Yi Song2
  • 1: Hunan Seefore Information Technology Co.
  • 2: College of Intelligence and Computing
*Contact email: bo_wang@tju.edu.cn

Abstract

Most methods of emotional dialogue generation focus on how to make the generated replies express the set emotion categories, while ignoring the control over the semantic content of the replies. To this end, in this paper, we propose a emotion- and content-controllable response generation model, ECCRG. ECCRG allows for text-controlled conditions and integration into the decoding process of the language model through a self-attention layer, enabling more precise control over the content of the generated responses. We use a variety of optimization objectives including self-reconfiguration loss and adversarial learning loss to jointly train the model. Experimental results show that ECCRG can embody the set target content in the generated responses, allowing us to achieve controllability on both emotion and textual content.

Keywords
Dialogue systems Emotional response generation Controllable text generation
Published
2024-02-23
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-031-54528-3_7
Copyright © 2023–2025 ICST
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL