从人设到真人：在个性化对话生成中通过多话语关系图学习提升自然度
From Persona to Person: Enhancing the Naturalness with Multiple Discourse Relations Graph Learning in Personalized Dialogue Generation
AI总结：
针对个性化对话生成中回复需兼顾连贯性与人设一致性的挑战，提出MUDI方法，借助大语言模型构建对话图、用DialogueGAT捕捉话语关系，并通过连贯感知注意力提升生成质量，使回复更自然类人。
摘要：
在对话生成中，回复的自然度对高效人机交互至关重要。个性化回复生成面临更大挑战，因为回复必须保持连贯，且与用户的个人特质或人设描述相一致。我们提出用于个性化对话生成的MUDI（多话语关系图学习）方法。我们利用大语言模型辅助标注话语关系，将对话数据转换为结构化的对话图。我们提出的图编码器DialogueGAT模型随后在该结构中捕捉隐含话语关系以及人设描述。在个性化回复生成阶段，我们采用新颖的连贯感知注意力策略，增强解码器对话语关系的考量。我们的实验表明，个性化回复的质量得到显著提升，从而更接近类人对话交流。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
