Group Meeting | 2025-05-06
Date
May 6, 2025
Event
Group meeting
2 papers were presented at this group meeting.
Presenters
Papers and research themes
| Paper and research focus | Presenter | Publication | Resources |
|---|---|---|---|
RAKG:Document-level Retrieval Augmented Knowledge Graph ConstructionRAKG提供了一个从文档直接构建知识图谱的全面解决方案，首次将RAG评估框架引入知识图谱构建领域，开发了标准知识图谱和相应的评估方法，并在MINE数据集上取得了95.91%的准确率，比当前最佳基线GraphRAG（89.71%）提高了6.2个百分点。 |  @Yizhe Li | arXiv 2025-04 | Not available |
Deep learning for cross-domain data fusion in urban computing: Taxonomy, advances, and outlook该论文系统综述了基于深度学习的多模态数据融合方法在城市计算中的应用，将现有方法分为四类：特征融合、对齐融合、对比融合与生成融合；将城市应用归纳为七大领域，并强调深度学习方法与城市计算任务的协同，同时也引入了大语言模型在其中的应用。 |  @Qiang Xia | Information Fusion 2024-05 | Not available |