HyPE：基于类别感知的超图编码与持久边嵌入用于人物角色对话
HyPE: Category-Aware Hypergraph Encoding with Persistent Edge Embeddings for Persona-Grounded Dialogue
AI总结：
提出HyPE框架，通过将人物角色文本解析为四元组并构建超图，利用HyperGCN和持久边嵌入（PEE）编码高阶关系，在PersonaChat上优于句子级池化基线。
摘要：
人物角色对话系统旨在生成与说话者角色一致的回复，但现有方法将角色视为一组扁平句子，未能建模角色属性间的高阶关系——例如，多个角色句子共享一个主题类别。我们提出HyPE（超图角色编码器）框架，该框架（i）将每个承载角色的文本分析为（核心、表达、情感、类别）四元组，以及（ii）将角色元素组织成一个超图，其超边由共享类别标签诱导。HyperGCN超图神经网络将此结构传播为角色摘要向量和软记忆库，以条件化回复生成器。我们进一步提出持久边嵌入（PEE），即轻量级的每类别可学习先验，融合到HyperGCN的消息传递步骤中。在贪婪解码下的PersonaChat上，HyPE在GPT-2、LLaMA-3.2-3B和Qwen2.5-3B骨干网络上一致优于句子级池化基线，表明结构化的超边级角色编码在不同模型规模上提供了可迁移的优势。
英文摘要：
Persona-grounded dialogue systems aim to produce responses consistent with a speaker's persona, yet existing methods treat personas as a flat set of sentences and fail to model the high-order relations among persona attributes-e.g., that several persona sentences share a topical category. We propose HyPE (Hypergraph Persona Encoder), a framework that (i) analyzes each persona-bearing text as a (Core, Expression, Sentiment, Category) quadruple, and (ii) organizes persona elements into a hypergraph whose hyperedges are induced by shared category labels. An HyperGCN hypergraph neural network propagates this structure into a persona summary vector and a soft-memory bank that condition the response generator. We further propose Persistent Edge Embeddings (PEE), lightweight per-category learnable priors fused into the HyperGCN message-passing step. On PersonaChat under greedy decoding, HyPE consistently outperforms sentence-level pooling baselines across GPT-2, LLaMA-3.2-3B, and Qwen2.5-3B backbones by demonstrating that structured hyperedge-level persona encoding provides a transferable advantage across model scales.
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。
