| 学科背景知识在医学文本特征抽取中的应用 |
| |
| 引用本文： | 赵迎光,范少萍,安新颖. 学科背景知识在医学文本特征抽取中的应用[J]. 医学信息学杂志, 2017, 38(4): 50-54,81 |
| |
| 作者姓名： | 赵迎光 范少萍 安新颖 |
| |
| 作者单位： | 中国医学科学院医学信息研究所 北京 100020;中国医学科学院医学信息研究所 北京 100020;中国医学科学院医学信息研究所 北京 100020 |
| |
| 基金项目： | 国家自然科学基金项目“基于语义的医学领域前沿知识发现及演化机制研究”（项目编号：71303259）；中央级公益性科研院所基本科研业务费“面向医学科技评价的多源异构数据处理机制研究”（项目编号：2016ZX33 0027）。 |
| |
| 摘 要： | 分析目前科技文献文本特征抽取方法研究现状，将基于背景知识的TF-IDF方法应用到医学文本特征抽取中，在4个医学领域中进行试验对比，结果表明该方法在抽取词汇数量较少时可以显著提高抽取效果，在对文本集合中通用词的过滤及重要特征词的识别方面明显优于使用通用IDF的TF-IDF方法。
|
| 关 键 词： | 文本挖掘 TF-IDF 特征抽取 知识发现 |
| 收稿时间： | 2016-12-23 |
Application of Disciplinary Background Knowledge in Medical Text Feature Extraction |
| |
| ZHAO Ying-guang,FAN Shao-ping and AN Xin-ying. Application of Disciplinary Background Knowledge in Medical Text Feature Extraction[J]. Journal of Medical Informatics, 2017, 38(4): 50-54,81 |
| |
| Authors: | ZHAO Ying-guang FAN Shao-ping AN Xin-ying |
| |
| Affiliation: | Institute of Medical Infromation, Chinese Academy of Medical Sciences, Beijing 100020, China;Institute of Medical Infromation, Chinese Academy of Medical Sciences, Beijing 100020, China;Institute of Medical Infromation, Chinese Academy of Medical Sciences, Beijing 100020, China |
| |
| Abstract: | The paper analyzes the conditions of research on the current scientific literature text feature extraction methods, applies the TF-IDF method based on background knowledge in the medical text feature extraction, and conducts experimental comparison in four medical fields. The result indicates that this method can obviously improve the extraction effect when there are few vocabularies to be extracted, and is obviously superior to the IDF based TF-IDF method in the aspects of filtration of commonly-used words in the text set and identification of important feature words. |
| |
| Keywords: | Text mining TF-IDF Feature extraction Knowledge discovery |
|
| 点击此处可从《医学信息学杂志》浏览原始摘要信息 |
|
点击此处可从《医学信息学杂志》下载全文 |
