论文部分内容阅读
[目的 /意义]构建基于关联数据的探索式检索系统,充分利用关联数据中隐藏的知识网络,向用户提供发现新知识的机会。[方法 /过程]基于DBpedia电影数据集,采用改进的向量空间模型进行关联数据的语义相似度计算,使用可视化的交互技术对检索结果进行呈现。[结果 /结论]通过基于任务的评价方法与IMDB进行对比,证明基于关联数据的探索式检索系统能够提高检索效率,提升用户体验并能引导用户发现其感兴趣的信息。
[Purpose / Significance] To construct an exploratory retrieval system based on related data, and make full use of the hidden knowledge network in the related data to provide users with the opportunity to discover new knowledge. [Methods / Processes] Based on the DBpedia movie dataset, the improved vector space model is used to calculate the semantic similarity of related data and the visualization of interactive results is used to present the retrieval results. [Results / Conclusion] The task-based evaluation method is compared with IMDB to prove that the exploratory search system based on related data can improve the retrieval efficiency, enhance the user experience and guide the user to find out the information they are interested in.