Miracle: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control
Zhenyi Lu, Wei Wei, Xiaoye Qu, Xian-Ling Mao, Dangyang Chen, Jixiong Chen · 2023
Personalized dialogue systems aim to endow the chatbot agent with more anthropomorphic traits for human-like interactions.Previous approaches have explored explicitly user profile modeling using text descriptions, implicit derivation of user embeddings, or utilizing handicraft prompts for ChatGPT-like models.However, textual personas are limited in describing multi-faceted attributes (e.g., language style, inner character nuances), implicit embedding suffers from personality sparsity, and handicraft prompts lack fine-grained and stable controllability.Hence, these approaches may struggle with complex personalized dialogue generation tasks that require generating controllable responses with multiple personal attributes.To this end, we propose MIRACLE, a novel personalized dialogue generation method through MultIple PeRsonal Attributes Control within Latent-Space Energybased Models.Specifically, our approach first disentangles complex personality into multifaceted attributes.Subsequently, we employ a conditional variational auto-encoder to align with the dense personalized responses within a latent joint attribute space.We have also tailored a dedicated energy function and customized the ordinary differential equations sampling method to offer flexible attribute composition and precise attribute control.Extensive experiments demonstrate that MIRA-CLE outperforms state-of-the-art models regarding both personality controllability and response generation quality.Our dataset and code are available at https://github.com/ LZY-the-boys/MIRACLE