
Research Article
ECCRG: A Emotion- and Content-Controllable Response Generation Model
@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
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.