自然语言文档复制检测研究综述.pdfVIP

1000-9825/2003/14(10)1753 ©2003 Journal of Software 软 件 学 报 Vol.14, No.10 自然语言文档复制检测研究综述 + 鲍军鹏, 沈钧毅, 刘晓东, 宋擒豹 (西安交通大学 计算机科学与技术系, 陕西 西安 710049) A Survey on Natural Language Text Copy Detection + BAO Jun-Peng , SHEN Jun-Yi, LIU Xiao-Dong, SONG Qin-Bao (Department of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710049, China) + Corresponding author: Phn: 86-29-3042054, E-mail:baojp@ Received 2002-09-03; Accepted 2003-05-27 Bao JP, Shen JY, Liu XD, Song QB. A survey on natural language text copy detection. Journal of Software , 2003,14(10):1753~1760. /1000-9825/14/1753.htm Abstract: Copy detection has very important application in both intellectual property protection and information retrieval. Currently, copy detection concentrates on document copy detection mainly. In early days, document copy detection concentrated on program plagiarism detection mainly and now the most studies are on text copy detection. In this paper, a comprehensive survey on natural language text copy detection is given, the developments of copy detection is introduced. The approaches and features of a variety of existing text copy detection systems or prototypes are reviewed in detail. Then some key detection techniques are listed and compared with each other. In the end, the future trend of text copy detection is discussed. Key words : copy detection; plagiarism; intellectual property protection; information retrieval 摘 要: 复制检测技术在知识产权保护和信息检索中有着重要应用.到目前为止,复制检测技术主要集中在文档 复制检测上.文档复制检测在初期主要检测程序复制,现在则主要为文本复制检测.分别介绍了程序复制检测和文本 复制检测技术的发展,详细分析了目前已知各种文本复制检测系统的检测方法和技术特点,并比较了各系统关键技 术的异同,最后指出了文本复制检测技术的发展思路. 关键词: 复制检测;剽窃;知识产权保护;信息检索 中图法分类号: TP309 文献标识码: A 复制检测(copy detection)又称剽窃检测(plagiarism detection),也有人称为副本检