节点文献
基于实体识别的在线主题检测方法
On-Line Topic Detection Using Named Entity Recognition
【摘要】 为提高在线主题的检测效率,作者提出了一种基于实体识别技术的在线主题检测方法,利用新闻报道中的命名实体快速判断新到达报道与历史主题的关系,从而减少对报道间文本相似度的计算。实验结果显示,本文提出的方法能够在不牺牲检测准确率的基础上,显著提高在线主题检测的效率。
【Abstract】 In order to make on-line topic detection more efficient,a new method is proposed based on named entity recognition. New method extracts news elements from stories. Based on news elements,query composition is used to detect story link. This process reduces complex computation of text similarities. Experimental result indicates that the proposed method performs on-link topic detection accurately and efficiently.
【关键词】 在线主题检测;
命名实体;
实体识别;
增量聚类;
后缀树聚类;
【Key words】 on-line topic detection; named entity; named entity recognition; incremental clustering; suffix tree clustering;
【Key words】 on-line topic detection; named entity; named entity recognition; incremental clustering; suffix tree clustering;
【基金】 国家自然科学基金(60473051,60503037);国家高技术研究发展计划专项经费(2006AA01Z230,2007AA01Z191)资助
- 【文献出处】 北京大学学报(自然科学版) ,Acta Scientiarum Naturalium Universitatis Pekinensis , 编辑部邮箱 ,2009年02期
- 【分类号】TP391.1
- 【被引频次】6
- 【下载频次】344