摘要
首先从古籍的智能整理、智能检索和智能翻译等三个方面论述古籍数字化标注资源建设的重要意义。其次在搜集整理当前研究成果的基础上,从古籍的分词与词性标注、古籍的句法标注等两个方面对古籍数字化标注资源的建设现状进行概述。最后对当前的研究现状进行对比分析,探讨其中存在的问题,并且同给出了一些可行的解决措施。
Firstly, important meanings of the annotated and digitalized resources development of ancient books are reviewed from the aspects of the intelligent collation, retrieval and translation. Secondly, based on investigating current achievements, the recent progress in the annotated and digitalized resources development of ancient books are introduced from the aspects of word segmentation and part-of-speech tagging and syntax annotation. Finally, a comparative study of some similarities and differences among current research results are reported, several problems of current research results are discussed, and some suggestions related to these problems are proposed.
出处
《图书馆学研究》
CSSCI
2016年第4期49-52,36,共5页
Research on Library Science
基金
教育部人文社会科学研究青年基金项目"基于中文信息处理技术的古籍整理研究"(项目编号:12YJC870008)
江苏省社科研究文化精品课题"基于文字图像分析技术的珍贵古籍数字化方法的研究"(项目编号:12SWC-030)的研究成果
关键词
古籍数字化
标注资源
中文分词
digitization of ancient books annotated resources Chinese word segmentation