基于中文电子病历的跨科室组块分析

被引：3

作者：

戴雪

蒋志鹏

关毅

机构：

[1] 哈尔滨工业大学计算机科学与技术学院

来源：

计算机应用研究 | 2017年 / 34卷 / 07期

关键词：

中文电子病历; 词性标注; 组块分析; 领域适应; 结构化支持向量机;

D O I：

暂无

中图分类号：

TP391.1 [文字信息处理];

学科分类号：

摘要：

针对医疗领域的研究,发现了不同科室间电子病历存在着差异,但是新语料的标注成本又非常高。为了解决这一问题,利用迁移学习的方法在中文电子病历中进行跨科室组块分析的研究。在构建的中文电子病历中,对比了SSVM与CRF模型在词性标注和组块分析上的实验结果,发现SSVM模型的效果更好并选择该模型作为基本标注模型;此外,使用了改进的结构对应学习算法(SCL)进行组块分析,使得该算法能适用于SSVM模型进行领域适应。实验结果表明该算法有效地改善了序列标注任务中跨科室的领域适应性问题。

引用

页码：2084 / 2087

页数：4

共 22 条

[1] RES[P]. 澳大利亚专利:AU5679373A,1974-12-12
[2] Co-clustering based classification for out-of-domain documents. Wenyuan Dai,Guirong. Xue,Qiang. Yang,Yong. Yu. Proceedings of the Thirteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . 2007
[3] Support Vector Machine Learning for Interdependent and Structured Output Spaces. G.Bakir,T.Hofmann,B.Scholkopf,et al. International Conference on Machine Learning . 2005
[4] Using co-training and self-training in semi-supervised multiple classifier systems. Didaci L,Roli F. Proc of Joint IAPR International Conference on Structural,Syntactic,and Statistical Pattern Recognition . 2006
[5] Unregistered biological words recognition by Q-learning with transfer learning. Zhu Fei,Liu Quan,Wang Hui,et al. Scientific World . 2014
[6] Auxiliary problems selection in Chinese semantic role labeling. Zhang, Taozheng,Wang, Xiaojie,Tong, Hui,Zhong, Yixin. Journal of Computational Information Systems . 2012
[7] Conditional random fields: probabilistic models for segmenting and labeling sequence data. Lafferty J,McCallum A,Pereira F. Proceedings of the Eighteenth International Conference on Machine Learning . 2001
[8] Domain adaptation with structural correspondence learning. Blitzer, J,McDonald, R,Pereira, F. Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing . 2006
[9] Medical Entity Recognition:A Compari-son of Semantic and Statistical Methods. Abacha A B,Zweigenbaum P. Proceedings of BioNLP2011Workshop . 2011
[10] Developing a linguistically annotated corpus of Chinese electronic medical record. Jiang Z,Zhao F,Guan Y. IEEE International Conference on Bioinformatics and Biomedicine (BIBM) . 2014

← 1 2 3 →