节点文献
古籍数字化关键技术评述
Key Technologies for Digitization of Ancient Chinese Books
【摘要】 中国历史文化典籍是中华民族的宝贵财富。在数字环境下,实现古籍的数字化整理与利用,能够为数字人文研究、历史学研究及其他人文研究提供基础性资源,也是推动中华文明创造性转化与创新性发展的重要依托。古籍的数字化整理包括纸本资源的电子化,以及在电子化文本基础上的断句、标点、词语切分等基础性加工和深层知识提取。本文对现有古籍数字化整理的技术方法与平台进行梳理与评述,分析古籍数字化整理的挑战,探讨古籍数字化整理任务的未来发展方向。
【Abstract】 Chinese historical and cultural classics are the great treasure of the Chinese nation. In the digital environment,the realizationofdigital documentationand utilization of ancient books can provide basic resources for digital humanities research,history research and other humanities researches,and it also serves as an important support for promoting the creative transformation and innovative development of Chinese civilization. The work of digitizationincludes the electronizationof paper resources,as well as basic processing and deep knowledge extraction such as sentence segmentation,punctuation,and word segmentation based on electronic texts. This article reviews and comments on the existing technical methods and platforms of the digital collation of ancient books,analyzesits challenges,and discusses its future development direction.
【Key words】 collation of ancient books; digitization of ancient books; Natural Language Processing; digital humanities;
- 【文献出处】 数字人文研究 ,Digital Humanities Research , 编辑部邮箱 ,2021年03期
- 【分类号】G255.1
- 【被引频次】3
- 【下载频次】707