摘要
古籍目录辨章学术,考镜源流,对古典学术研究具有重要的价值。本文提出古籍提要网络分析模型,用无向三部图整合古籍、人物和提要信息。在此基础上构建古籍目录智能分析工具,不仅可以自动挖掘提要中蕴藏的人物关系,与已有的古代人物知识库相关联,为知识库补充可靠而有价值的关系信息;而且综合考虑提要的元数据和正文的语义特征信息,并将其整合入推荐算法中,能为用户智能地推荐与被检索项内容、部类名、古籍名、古籍责任者相关的提要。以《四库全书总目》为实验数据集,一方面基于提要网络,从人物、古籍、提要三个层面探索不同实体间的内在联系,并就四部提要中出现的人名和古籍名开展定量研究;另一方面从作者简介、内容概述及学术评价这三种提要文本特征入手,结合元数据信息和三种常用的文献推荐算法,评估不同的语义特征对工具推荐功能准确性的影响。实验结果表明,提要文本中的内容概述及学术评价作为语义特征提炼,再结合元数据信息,效果良好,可推广应用到面向古籍的知识发现中。
Catalog annotations in Chinese rare-book collections also known as Tiyaos contain the essential information regardinga book e.g.the author introduction the summary the nature and style the version and the critique of the corresponding book.In order to write a good Tiyao even the most eminent scholars spent a lotof time and effort in collecting collating reviewing and annotating large-scale book collections.However confronted with large-scale rare-book collections even though we pay huge human efforts on writing editing and recommending Tiyaos this task is still time-consuming and omissions are inevitable.In thispaper we propose a Tiyao-centric network model which integrates rare-books historic and Tiy aosinto one tripartite graph.This network model is not limited to the language or scale of figurestexts and can befurther applied to large-scale catalogues of rare-book collections.Bas ed on this model we construct a Tiyao explorative tool TiyaoX.By using SPARQL this tool can extract RDF data in related knowledge bases and provide users with information of rare-book authors or editors for inst ance occupation imperial examination biography and so on.Furthermore this tool can automatically extract theindividual relations embedded in Tiyaos enrich the existing resources with reliable and valuable relation information in addition this tool leverages metadata and content features of Tiyaos to recommend potentialinter esting and query-relevant e.g.Tiyao content category book name and author relevant Tiyaos.Inthis paper we use Siku Quanshu Zongmu as dataset and on the one hand we investigate the latent relations among rare-books historic figures andTiyaos.We also make separate quantitative analysis towa rdsperson names and book names in four divisions of this dataset respectively.The results demonstrate that Tiy aos in.Ji division contain most name s of historical persons and books and Tiyaos in.Jing divisioncontain names least.Tiyaos in.Zi and.Ji divisions have the maximum overlap of person names andTiyaos in.Shi and.Zi divisions have the maximum overlap of book names.In the constructed network m ost key figures are Confucius scholars book collectors and bibliographers and most important rare-books are descriptive catalogues Confucian classics and history books.On the other hand we take advantage of descriptive features in Tiyao content author introduction content summary and critics and combinethem with Tiyao mea tada as well as three text recommendation strategies Cosine similarity LDA+JS distance and Word2 Vec+RWMD.Our objective is to evaluate the impacts of different content features ont he accuracy of recommendation module of TiyaoX respectively.The experimental results demonstrate thatthe approach that integrates summary critique information and Tiyao metadata information as content featu resperform sbest among all results.This approach can be extended to knowledge discovery of rarebook collections which provides convenience for related professionals scholars and enthusiasts and improves efficiency in practice.
作者
李惠
陈涛
侯君明
刘丁
朱庆华
刘炜
LI Hui;CHEN Tao;HOU Junming;LIU Ding;ZHU Qinghua;LIU Wei
出处
《中国图书馆学报》
CSSCI
北大核心
2021年第4期97-112,共16页
Journal of Library Science in China
关键词
古籍目录
提要
网络模型
智能分析工具
数字人文
Catalogs in Chinese rare-book collections
Tiyao
Network model
Explorative tool
Digital humanities
作者简介
通信作者:李惠,上海图书馆(上海科学技术情报研究所),南京大学信息管理学院博士后。上海20003,Email:lh9743@126.com,0RCID:0000-0001-7050-1845;陈涛,中山大学信息管理学院副教授。广东广州510006;侯君明,上海古籍出版社编辑。上海200001;刘丁,天津工业大学计算机科学与技术学院讲师。天津300061;朱庆华,南京大学信息管理学院教授。江苏南京210023;刘炜,上海图书馆(上海科学技术情报研究所)研究员。上海200031。
