摘要语言视角下医学突破性论文识别研究  

Study on Identification of Medical Breakthrough Papers from the Perspective of Abstract Language

作　　者：林紫洛 杨雪梅 于诗睿 陈逸菲 唐小利[1] LIN Ziluo;YANG Xuemei;YU Shirui;CHEN Yifei;TANG Xiaoli(Institute of Medical Information&Library,Chinese Academy of Medical Sciences&Peking Union Medical College,Beijing 100005,China)

机构地区：[1]中国医学科学院/北京协和医学院医学信息研究所/图书馆,北京100005

出　　处：《医学信息学杂志》2023年第5期39-44,共6页Journal of Medical Informatics

基　　金：中国医学科学院医学与健康科技创新工程“生物医学文献信息保障与集成服务平台”(项目编号:2021-I2M-1-033);国家科技图书文献中心专项“下一代开放知识服务平台关键技术优化集成与系统研发”(项目编号:2022XM28)。

摘　　要：遴选具有代表性的突破性论文集,分析论文摘要语言学特征,提取特征句式并划分摘要语步,利用深度学习算法构建医学突破性论文摘要识别模型。实证结果表明模型在具体医学领域中适用,为突破性论文早期发现提供参考。A representative collection of breakthrough papers is selected, the linguistic features of abstracts are analyzed, and the characteristic sentence patterns are extracted and the abstract moves are divided. Thus, an abstract recognition model for medical breakthrough papers is constructed by using deep learning algorithm. The empirical results show that the model is applicable in specific medical fields and provides references for early discovery of breakthrough papers.

关 键 词：突破性论文 摘要文本 语言学特征 自动识别 

分 类 号：R-058[医药卫生]