检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:李章超 何琳[3] 喻雪寒 LI Zhangchao;HE Lin;YU Xuehan
机构地区:[1]江苏开放大学公共管理学院 [2]江苏开放大学江苏基层社会治理研究协同创新基地 [3]南京农业大学信息管理学院
出 处:《图书馆论坛》2024年第4期125-137,共13页Library Tribune
摘 要:在数字化背景下,整合海量、多源和异构的典籍内容知识资源,并从中抽取与典籍内容相关的知识单元,揭示知识之间的相互关系,成为还原历史事件所处复杂情境的关键。文章尝试从知识组织角度出发,利用历史学者需求调查、LDA主题模型聚类和本体复用等方法构建典籍内容知识表达模型;提出包括事件及其论元构成和事件关系抽取的事理图谱自动化构建方法,从内容和应用的维度实现事理图谱的质量评估。在此基础上,从主题叙事、空间叙事和逻辑叙事的定义域视角,实现典籍内容知识应用。本文构建的典籍内容事理图谱能从更细粒度实现事件与角色、地点、时间和万物的结构化和语义化描述,在实现典籍内容事件知识序化的同时,充分揭示历史事件的分布规律与发展趋势。In the context of digitalization,integrating massive,multi-source,heterogeneous knowledge of ancient books,extracting the knowledge units,and revealing the interrelationships among the knowledge have become the key to restoring the complex circumstances in which historical events took place.From the perspective of knowledge organization,this study attempts to build a knowledge representation model of Chinese classics based on a survey of historical scholars’needs,using methods of LDA topic model clustering and ontology reuse.It proposes an automated method to extract events,arguments and relationships,and achieves the quality evaluation of the event knowledge graph in terms of content and application.Thus,the knowledge in classical books can be used from the perspective of thematic,spatial and logical narratives.The event knowledge graph proposed in this paper gives a more fine-grained structural and semantic description of events,roles,places,time and everything,and fully reveals the distribution pattern and development trend of historical events while fulfilling the sequencing of event knowledge in ancient classics.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.49