CORC  > 清华大学
基于时空分析的线索性事件的抽取与集成系统研究
吴平博 ; 陈群秀 ; 马亮 ; WU Ping-bo ; CHEN Qun-xiu ; MA Liang
2010-07-15 ; 2010-07-15
会议名称全国第八届计算语言学联合学术会议(JSCL-2005)论文集 ; 全国第八届计算语言学联合学术会议(JSCL-2005) ; 中国南京 ; CNKI ; 南京师范大学、清华大学智能技术与系统国家重点实验室
关键词信息抽取 句型模板 线索性事件 时空信息 事件合并 infonnation extraction, sentence pattern, developing event, space-time information, merging event TP391.1
其他题名Research on Extraction and Integration of Developing Event Based on analysis of Space-time Information
中文摘要信息抽取技术能够提供高质量的检索服务。本文面向网络新闻事件,对人们感兴趣的事件关键信息进行了抽取和集成。系统中采用了如下的方法、策略:(1)利用句型模板构造抽取规则,然后直接从经过时间短语和空间短语识别和规范化处理的文本中抽取事件信息,从而跳过了深层句法分析,降低了实现系统的难度;(2)利用事件的规范化的时空信息关联不同文档中的同一事件,进行事件合并;(3)文档发生事件转移时对文档进行事件切分,从而解决了文档内不同事件信息的归并问题。初步实验结果表明:本文采用的方法和策略是有效的,抽取结果达到了国内外事件抽取的先进水平,而线索性事件集成的研究则是一种创新尝试.; Technology of information extraction (IE) can provide excellent service for retrieval. This paper oriented to the events in web news implements a system that can extract and integrate key information of event that interests people. Means and strategies of the system are as follows: (1) Extraction rules are built by sentence patterns, then event information is directly extracted from the text in which temporal phrases (TP) and space phrases (SP) are recognized and normalized specially. So the extraction system is easily implemented owing to skipping complex syntax parsing. (2) The same event in different documents is related by normalized TP and SP of event, therefore the information belonged to an event is merged. (3) When new event appears in a text, the text is segmented. So isolative information for an event in same segment can merge its owner. Primary experiments show that means and strategies in this paper are feasible, and the extraction result basically achieves advanced level in the world, otherwise the research of integration for developing event is an innovative work.; 本文承国家863项目资助(NO.2001AA114040)
会议录出版者清华大学出版社
语种中文 ; 中文
内容类型会议论文
源URL[http://hdl.handle.net/123456789/69915]  
专题清华大学
推荐引用方式
GB/T 7714
吴平博,陈群秀,马亮,等. 基于时空分析的线索性事件的抽取与集成系统研究[C]. 见:全国第八届计算语言学联合学术会议(JSCL-2005)论文集, 全国第八届计算语言学联合学术会议(JSCL-2005), 中国南京, CNKI, 南京师范大学、清华大学智能技术与系统国家重点实验室.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace