通过构建对话图结构提升个性化对话自然度
From Persona to Person: Enhancing the Naturalness with Multiple Discourse Relations Graph Learning in Personalized Dialogue Generation
- 用大模型标注对话关系，构建结构化对话图
- 图注意力网络捕捉隐含对话关联，提升回复一致性
- 适合研究个性化对话生成与人机交互的学者
在对话生成中，回复的自然性对人机交互至关重要。个性化对话生成挑战更大，需确保回复与用户个性特征或人物描述保持一致。本文提出MUDI（多话语关系图学习）方法，利用大语言模型辅助标注话语关系，并将对话数据转化为结构化对话图。所提出的DialogueGAT图编码器在此结构上捕捉隐含的话语关系及人物描述信息。在个性化回复生成阶段，采用新颖的连贯性感知注意力机制，增强解码器对话语关系的关注。实验表明，该方法显著提升了个性化回复质量，使对话更接近人类交流风格。
原文摘要 · Abstract (English)
In dialogue generation, the naturalness of responses is crucial for effective human-machine interaction. Personalized response generation poses even greater challenges, as the responses must remain coherent and consistent with the user's personal traits or persona descriptions. We propose MUDI ($\textbf{Mu}$ltiple $\textbf{Di}$scourse Relations Graph Learning) for personalized dialogue generation. We utilize a Large Language Model to assist in annotating discourse relations and to transform dialogue data into structured dialogue graphs. Our graph encoder, the proposed DialogueGAT model, then captures implicit discourse relations within this structure, along with persona descriptions. During the personalized response generation phase, novel coherence-aware attention strategies are implemented to enhance the decoder's consideration of discourse relations. Our experiments demonstrate significant improvements in the quality of personalized responses, thus resembling human-like dialogue exchanges.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。