【作者】 周小甲； 李昊旻； 吕旭东； 段会龙；

【Author】 ZhouXiaoJia LiHaoMin* LuXuDong DuanHuiLong(College of Biomedical Engineering and Instrument Science,The Key Laboratory of Biomedical Engineering,Ministry of Education Zhejiang University,Zhejiang Hangzhou 310027)

【机构】 浙江大学生物医学工程与仪器科学学院生物医学工程教育部重点实验室；

【摘要】 时间表达式识别是时序语义标注的关键技术之一,其结果的好坏直接影响时间信息后续利用的效果。国外相关领域研究成果不能直接应用于中文,国内此领域的研究大多针对新闻语料,无法满足医学领域的时间表示识别要求,因此专门针对医学病历语料的时间表达识别研究是进行中文病历文本中时间信息利用的必经阶段。本文对涵盖30多个科室的147份实际病历中的时间表达进行统计并分类,进而分析中文病历中时间信息表达的特点。根据分析结果,本文提供了针对中文病历中时间信息的识别方法,实验表明本文采用的正则匹配方法以及相邻原则匹配复合时间的方法能基本覆盖时间表达信息,以上工作对后续中文病历中时间信息的利用工作具有重要意义和参考价值。更多还原

【Abstract】 Recognizing time expressions is one of the key technologies for temporal semantic annotation,and the recognizing results have directly effects to the further usage of temporal information.The international achievements of related area don’t fit to Chinese corpus,and the domestic studies are oriented to news articles,which can’t meet the needs of recognizing time expressions in medical area.Consequently,it’s necessary to study the methods of recognizing time expressions oriented to Chinese narrative medical records,which is an inevitable stage to the usage of temporal information in Chinese narrative medical records.Firstly,this study made a statistic and classification to 147 shares of practical medical records covering more than 30 section offices,and made an analysis to the pattern of time expressions in Chinese medical records.Based on the analytic results,this study proposed a method which applied regular expressions to recognize time expressions in Chinese medical records,and applied the proximity principle to recognize composite time expressions.The recognizing results showed that the method we proposed could cover most time expressions in the corpus referred above,and this study made an important significance and important reference value for further use of temporal information in Chinese narrative medical records.更多还原