Apply Language Nature Rhythm to Large Scale Duplicated Text Detection

摘要：

It is urgent that detect the duplication in large scale text in the Web. An arithmetic based on language rhythm for text duplication detection is proposed here. Get the nature rhythm marked by punctuations in text and build the rhythm compare matrix to complete the publication detection for each paragraph. This arithmetic is different with the other one which is based on words analysis. And it has a high accuracy and a low complicacy.

关键词： Duplicated text detection language nature rhythm punctuation

作者: Chen Fan Feng Zhiyong Zhao Geng

作者单位: School of Computer Science and Technology, Tianjin University Information Science & Technology Depar School of Computer Science and Technology, Tianjin University Hebei University of Technology Tianjin, china

会议类型: 国际会议

会议名称: 2011 International Conference on Advanced Materials and Engineering Materials(2011先进材料与工程材料国际会议 ICAMEM 2011)

会议地点: 沈阳

会议语种:英文

页码: 635-640

在线出版日期: 2011-11-22（万方平台首次上网日期，不代表论文的发表时间）