汉语信息抽取中事件的定位与分类

被引:2
作者
邓擘 [1 ]
郑彦宁 [1 ]
樊孝忠 [2 ]
机构
[1] 中国科学技术信息研究所
[2] 北京理工大学计算机系
关键词
信息抽取; 事件; 特征词; 文本片段;
D O I
10.16353/j.cnki.1000-7490.2009.10.005
中图分类号
TP391.1 [文字信息处理];
学科分类号
081203 ; 0835 ;
摘要
事件抽取是信息抽取的基本任务之一,而对文本中的事件准确定位和分类是保证事件抽取质量的前提。使用向量空间模型来表示事件描述片段的特征,并分类计算特征词的重要度,最后对文本中的事件片段进行定位和分类。试验结果表明该方法能够对文本中的事件片段进行较为准确的定位、分类,因此对于事件抽取任务的前期处理具有重要价值。
引用
收藏
页码:104 / 107
页数:4
相关论文
共 8 条
[1]  
Applying semantic classes in event detection and tracking. Makkonen,J,Ahonen-Myka,H,Salmenkivi,M,Sangal,R,Bendre,SM. Proceedings of International Conference on Natural Language Processing (ICON) . 2002
[2]  
Newevent detection wi th nearest neighbor,support vector machines and kernel regres-sion. ZHANG J,YANG Y,CARBONELL J. Technical Report CMU-CS-04-118 . 2007
[3]  
Parameter free bursty ev ents detection in text streams. FUNG G P C,YUJ X,YUP S,et al. VLDB’05 . 2005
[4]  
Text classification and named enti-ties for new event detection. KUMARAN G,ALLAN J. Proceedings of the27th An-nual International ACMSIGIR Conference . 2004
[5]  
Event and sentiment detection in financial mar kets. HELLINGER U. ESWC08 . 2008
[6]  
Classification mod-els for new event detection. KUMARAN G,ALLANJ,MCCALLUMA. CIKM2004 . 2004
[7]  
Event information extraction using link grammar. MADHYASTHA H V,,BALAKRISHNAN N,RAMAKRISH-NAN K R. 13th International WorkShop on Research Issues in Data Engineering:Multi-lingual Information Management(RIDE‘03) . 2003
[8]  
Semantic language models for topic detection and tracking. Nallapati R. Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology: Proceedings of the HLT-NAACL 2003 student research workshop . 2003