Miracle: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control
Submission Type: Regular Long Paper
Submission Track: Dialogue and Interactive Systems
Submission Track 2: Natural Language Generation
Keywords: personalized response generaion, dialogue, Natural language generation
Abstract: 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 (\emph{e.g.}, \emph{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 \textbf{\textsc{Miracle}}, a novel personalized dialogue generation method through \textbf{M}ult\textbf{I}ple Pe\textbf{R}sonal \textbf{A}ttributes \textbf{C}ontrol within \textbf{L}atent-Space \textbf{E}nergy-based Models.
ttributes \textbf{C}ontrol within \textbf{L}atent-Space \textbf{E}nergy-based Models.
Specifically, our approach first disentangles complex personality into multi-faceted 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 \textsc{Miracle} outperforms several strong baselines in terms of personality controllability and response generation quality.
Our dataset and code are available at \url{https://github.com/LZY-the-boys/MIRACLE}
Submission Number: 1807
Loading