首页> 外文期刊>Journal of Computers >Web Page Classification Using Relational Learning Algorithm and Unlabeled Data
【24h】

Web Page Classification Using Relational Learning Algorithm and Unlabeled Data

机译:使用关系学习算法和未标记数据的网页分类

获取原文
           

摘要

—Applying relational tri-training (R-tri-training forshort) to web page classification is investigated in this paper.R-tri-training, as a new relational semi-supervised learningalgorithm, is well suitable for learning in web pageclassification. The semi-supervised component of R-tritrainingallows it to exploit unlabeled web pages to enhancethe learning performance effectively. In addition, therelational component of R-tri-training is able to describehow the neighboring web pages are related to each other byhyperlinks. Experiments on Web-Kb dataset show that: 1) alarge amount of unlabeled web pages (the unlabeled data)can be used by R-tri-training to enhance the performance ofthe learned hypothesis; 2) the performance of R-tri-trainingis better than the other algorithms compared with it.
机译:- 在本文研究了与网页分类的关系中的关系三训练(R-Tri-Training forshort).R-Tri-Training作为一种新的关系半监督学习,适合在Web PageClassification中学习。 R-TrutrainalOWS的半监督组件它可以利用未标记的网页以有效地增强学习性能。此外,R-Tri训练的其组成部分能够将相邻网页描述与彼此相关的Hyperlinks。 Web-KB数据集的实验表明:1)R-Tri培训可以使用未标记的网页(未标记数据)的Alarge金额,以提高学习假设的性能; 2)与其他算法更好的R-Tri-Training的性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号