基于条件随机场的《伤寒论》中医术语自动识别  

Automatic identification of TCM terminology in Shanghan Lun based on conditional random field

作　　者：孟洪宇[1] 谢晴宇[2] 常虹[3] 孟庆刚[1] 

机构地区：[1]北京中医药大学基础医学院,北京100029 [2]中国中医科学院中医临床基础医学研究所 [3]内蒙古包头医学院

出　　处：《北京中医药大学学报》2015年第9期587-590,共4页Journal of Beijing University of Traditional Chinese Medicine

基　　金：国家自然科学基金项目(No.81273876;No.81473800;No.81072897)

摘　　要：目的探索中医术语的自动识别方法,扩充中医文本的自然语言处理形式。方法采用基于条件随机场(CRF)的方法,针对《伤寒论》文本中的症状、病名、脉象、方剂等中医术语的自动识别标注问题,通过结合字本身、词性、词边界、术语类别标注的特征,分析不同特征组合对术语识别的影响,并探讨最具有效性的组合。结果以字本身、词边界、词性、类别标签为特征组合的中医术语识别模型准确率为85.00%,召回率为68.00%,F值为75.56%。结论字本身、词性、词边界、术语类别标注的多特征融合的模型识别效果最优。Objective To explore the methods of automatic identification of TCM terminology and to ex-pand the forms of natural language processing in TCM documents.Methods Based on the methods of conditional random field（ CRF） , annotation and automatic identification on terms of symptoms, diseases, pulse-types and prescriptions recorded in Shanghan Lun as the research subjects, the effects of different combinations of the features, such as Chinese character itself, part of speech, word boundary and term category label, on identification of terminology were analyzed and the most effective combination was selected.Results The TCM terminology automatic identification model, combining with the features of Chinese character itself, part of speech, word boundary and term category label, had the precision of 85.00%, recall of 68.00%and F score of 75.56%.Conclusion The multi-features model of combi-nation of Chinese character itself, part of speech, word boundary and the term category label achieved the best identifying result in all combinations.

关 键 词：中医术语 条件随机场 伤寒论 自动识别 

分 类 号：R222.19[医药卫生—中医基础理论]