[关键词]
[摘要]
目的 总结医药语料库发展趋势和研究热点,为中医及民族医命名实体识别和语义标注相关研究提供指导。方法 从中国知网、重庆维普、万方和Web Of Science数据库中检索近20年与医药语料库相关的文献。借助CiteSpace等软件对各年份发文量、发文国家(地区)、发文机构、作者、文献被引量、文献共被引和关键词进行分析。结果 筛选纳入中文文献462篇,英文文献122篇。中英文文献发文量均呈上升趋势;英文文献发文量最多的机构是法国科学研究中心;中文文献发文最多的机构是北京中医药大学。结论 目前中文文献研究主题集中在医学英语语料库建设,以及少量用于电子病历命名实体识别方面的语料库研究;英文文献研究主题集中在医药信息标注和命名实体识别工具开发。
[Key word]
[Abstract]
Objective To summarize the development trends and research hotspots of the medical corpus, and to provide guidance for research on named entity recognition and semantic annotation of Chinese medicine and ethnic medicine.Methods Documents related to medical corpus in the past 20 years were retrieved from CNKI, VIP, WANFANG and Web Of Science database. With the help of CiteSpace, the number of articles published in each year, research countries (regions), issuing organizations, authors, the number of citations, literature co-cited and keywords were analyzed.Results 462 Chinese documents and 122 English documents were screened and included. Both Chinese and English documents showed an upward trend; The institution that publishes the most English documents was Centre national de la recherche scientifique; The institution that publishes the most Chinese documents was Beijing University of Chinese Medicine.Conclusion At present, the research topics of Chinese literature mainly focused on the research of medical English corpus, and a small amount of corpus research used for the recognition of named entities in electronic medical records; English literature research topics focus on standardized labeling of medical information and development of named entity recognition tools .
[中图分类号]
[基金项目]
民族医防治常见病特色诊疗技法方药智慧医疗平台的建设