文档介绍：北京大学学报(自然科学版)
Acta Scientiarum Naturalium Universitatis Pekinensis

基于排序学习的文本概念标注方法研究
1,2,† 1,2 1,2 1,2
涂新辉何婷婷李芳王建文
1. 华中师范大学计算机学院, 武汉 430079; 2. 国家语言资源监测与研究中心网络媒体
语言分中心, 武汉 430079; † E-mai: tuxinhui@
摘要提出一种基于排序学习的方法来实现文档的维基百科概念自动标注。首先人工对一定规模的文档进行
概念标注, 建立训练集合, 然后利用排序学习算法在多项特征上得到对概念排序的模型, 利用这个概念的排
序模型对任意文档进行概念标注。实验表明, 相对于传统的文档概念标注方法, 此方法在各类指标上都有相
当大的提高, 标注结果更加接近人类的概念标注。
关键词概念标注; 排序学习; 维基百科; 显示语义分析
中图分类号 TP391
Learning to Annotate Text Using Wikipedia Concepts
TU Xinhui1,2,†, HE Tingting1,2, LI Fang1,2, WANG Jianwen1,2
1. School puter Science, Huazhong Normal University, Wuhan 430079; 2. Network Media Branch, National
Language Resources Monitoring and Research Center, Wuhan 430079; † E-mail: tuxinhui@
Abstract This paper proposed an automatic text annotation method based on learning to ranking model. Firstly
the authors built a training set of concept annotation manualy, and then used the Ranking SVM algorithm to
generate concept ranking model, finally the concept ranking model was used to generate concept annotation for any
texts. Experiments show that proposed method has a significant improvement in various pared to
traditional annotation methods, and concept annotation results is closer to human annotation.
Key words concept annotation; learning to ranking; Wikipedia; explicit semantic analysis
人类理解自然语言的过程是一个语义概念的联类