摘要
针对现有的通用信息抽取技术无法实现结构化的应急信息抽取和完整的地名地址识别的问题,该文提出了面向众源数据的地理信息抽取技术,采用了基于事件框架的应急信息抽取方法,利用层次模型与N-最短路径算法,解决了完整的地名地址的识别与提取的问题,较好地实现了应急地理信息的自动化抽取。通过实验的进一步分析,此方法取得了最优化的应急地理信息抽取结果。实验表明,基于事件框架的应急地理信息抽取技术不仅可以快速有效地抽取应急地理信息,还能够识别完整的地名地址。
In view of the problem that the common information extraction method cannot extract the structured emergency event information and recognize addresses accurately;the general information abstract tool cannot completely identify the emergency geographic information;these ways also do not have an accurate assessment of these results of extraction.So,this paper proposed an emergency information extraction technology based on event framework.This technique was to solve the problem of emergency information extraction.It mainly used a hierarchical model and the shortest path algorithm and allowed the toponomy pieces to be joined as a full address.The event framework was better to achieve the emergency geographic information extraction automatically.Through the further analysis of the experiment,this method obtained optimal emergency geographic information extraction results.Experiments showed that event frame technology could not only effectively extract the sources of emergency geographic information,but also identify the full name of the address.
出处
《测绘科学》
CSCD
北大核心
2017年第12期83-87,共5页
Science of Surveying and Mapping
基金
中国测绘科学研究院基本科研经费项目(7771615)
关键词
事件框架
应急
信息抽取
众源数据
层次模型
event framework
emergency
information extraction
crowdsourcing data
hierarchical model
