儒家古籍领域开展数字人文研究综述  

Review of Digital Humanities Research in the Field of Confucian Ancient Books

作　　者：谭泽霖 赵小兵[2,3] Tan Zelin;Zhao Xiaobing

机构地区：[1]中央民族大学中国少数民族语言文学学院,北京100081 [2]中央民族大学信息工程学院,北京100081 [3]国家语言资源监测与研究少数民族语言中心,北京100081

出　　处：《山东图书馆学刊》2025年第1期22-28,共7页The Library Journal of Shandong

基　　金：国家社科基金重大项目“多民族语言《十三经》跨学科研究及数据库建设”(项目编号:22&ZD035);中央民族大学博士研究生自主科研项目“儒家十三经信息可视化与知识发现研究”(项目编号:BZKY2024168)研究成果之一。

摘　　要：文章旨在梳理数字人文技术在儒家经典古籍研究中的应用现状和未来发展方向。以各种儒家典籍名称和“计算机”“深度学习”等关键词结合在数据库中进行文献检索。详细介绍了当前古籍数字化流程和古籍预训练模型的发展,从计算分析、文本分词、信息抽取、分类聚类、知识库构建角度对儒家古籍数字化技术进行归纳,并对古籍的发展方向进行展望。未来建议进一步开发多模态古籍大模型,加强古籍挖掘全面性,从文本信息的表层结构分析走向文化与思想的深层挖掘。The paper aims to review the current application status and future development direction of digital humanities technology in the study of Confucian classics and ancient books.Combining various Confucian classic names with keywords such as“computer”,“deep learning”for literature search in the database,the paper provides a detailed introduction to the current process of digitizing ancient books and the development of pre-training models for ancient books.Then,the paper summarizes the digitization of Confucian ancient books from the perspectives of computational analysis,text segmentation,information extraction,classification and clustering,and knowledge base construction.Finally,the paper looks forward to the future development of ancient books.In the future,it is recom-mended to further develop a multi-modal ancient book model,strengthen the comprehensiveness of ancient book mining,and further deepen the analysis from the surface structure of textual information to the deep exploration of culture and ideas.

关 键 词：数字人文 儒家古籍 数字化 

分 类 号：G255.1[文化科学—图书馆学]