弥合差距：用于统一多任务用户意图推理的双知识图谱框架
Mind the Gap: A Dual Knowledge Graph Framework for Unified Multi-task User Intent Inference
浏览论文内容
中文总结 AI 辅助
该研究针对在线旅游评论的多任务用户意图推理，提出DKG-MTI双知识图谱框架，结合动态构建的用户特定意图知识图谱与全局酒店知识图谱，经大语言模型处理后，在相关任务上优于现有基线。
中文摘要 AI 辅助
本文提出DKG-MTI，一种用于从在线旅游评论中进行统一多任务用户意图推理的双知识图谱框架。现有方法通常依赖分层流水线，存在误差传播问题，或依赖检索方法，忽略了领域知识中的结构关系。为解决这些局限，我们引入仅用于推理的知识增强框架，该框架从每条评论动态构建用户特定意图知识图谱，并通过感知结构的语义平滑将其与全局酒店知识图谱对齐。对齐后的知识与原始评论结合，经大语言模型处理，可同时预测方面评分并生成反向用户意图陈述。在TripAdvisor评论上的实验显示，DKG-MTI在分类和意图生成任务中均持续优于强大的大语言模型及基于检索的基线，证明了感知结构的知识对齐对可扩展且可解释的意图推理的有效性。
英文摘要
This paper proposes DKG-MTI, a dual knowledge graph framework for unified multi-task user intent inference from online travel reviews. Existing approaches often rely on hierarchical pipelines that suffer from error propagation or retrieval methods that ignore structural relationships in domain knowledge. To address these limitations, we introduce an inference-only knowledge augmentation framework that dynamically constructs a User-Specific Intent Knowledge Graph from each review and aligns it with a Global Hotel Knowledge Graph through structure-aware semantic smoothing. The aligned knowledge is combined with the original review and processed by a large language model to simultaneously predict aspect ratings and generate reverse user intent statements. Experiments on TripAdvisor reviews show that DKG-MTI consistently outperforms strong LLM and retrieval-based baselines in both classification and intent generation tasks, demonstrating the effectiveness of structure-aware knowledge alignment for scalable and explainable intent inference.
