Finding Plagiarism by Evaluating Document Similarities

2008 New Media Consortium Summer Conference

Jan Kasprzak ; Michal Brandejs ; Miroslav Kripac

Others  :  http://CEUR-WS.org/Vol-502/paper4.pdf
PID  :  2510

来源: CEUR

【 摘 要 】

In this paper we discuss the approach we have used for finding plagiarized passages of text during the PAN’09 plagiarism detection competition. We describe the existing anti-plagiarism system we use in the Czech National Archive of Graduate Theses. We then discuss the modifications to this system which havebeen necessary in order to fit the results to the competition rules. We also present a performance data of the described system, and the possible improvement for our production systems, which result from the code written for the PAN’09 competition.