摘要
个人简历(Curriculum Vitae,Vita)通常包含了丰富的数据,如个人信息、教育背景以及工作经历等。从大量的个人简历中抽取出有用的信息并提供检索服务,可以提供更加全面和完整的个人资料。个人简历中包含的信息可以看成是按时间排序的事件序列。进一步地,可以从不同的个人简历所包含的事件中挖掘出事件之间的关联关系。提出了一个从个人简历中提取并检索事件的框架,它可以自动地从互联网上搜索并下载个人简历文档,并从中提取出感兴趣的事件保存在数据库里,以进一步查询和检索事件。所完成的工作包括:(1)提出了一个事件表示模型,用于描述事件的基本属性及检索事件;(2)基于条件随机场提出了一个概率模型,用于从个人简历中自动提取事件;(3)通过挖掘事件属性之间的共现性,提出了基于事件的检索方法。
A curriculum vitae （henceforth referred to as a vita） usually contains a wealth of abundant data such as per- sonal information, educational background,publications and work experience. It is significant to search, extract and ex- plore the data from these vita documents which may provide a more comprehensive and integral personal profile. This personal profile can be viewed as a series of events. Moreover, we can take advantage of events from different individual＇s vita to explore and establish relationships between these events and the people involved. In this paper, we presented a framework extracting and explorating vita event, which can retrieve vita documents from the Internet, extract events from these documents and save the events to a database for further exploration. More concretely, the work introduced in this paper includes： （1） an event presentation model which characterizes the basic attributes of events and is utilized for event exploration; （2） a probabilistic model for extracting events from vita documents automatically; （3） an event explo- ration approach by exploiting the co-occurrence of the event attributes on the basis of the event presentation model and the event extraction approach.
出处
《计算机科学》
CSCD
北大核心
2012年第7期154-160,174,共8页
Computer Science
基金
国家自然科学基金(61040006)
湖北省自然科学基金(2010CDZ027)
湖北省教育厅科技项目(B20101909)资助
关键词
条件随机场
事件检索
事件抽取
事件表示
Conditional random fields,Event retrieval, Event extraction, Event presentation
