Plagiarism detection in a multilingual environment

Abstract

The purpose of this paper is to research an automatic similarity and plagiarism detection system in a multi-lingual environment. It was developed a new system that is using Winnowing fingerprint extraction method and overlapping word-5-grams algorithm to obtain the fingerprint of the documents. A language guesser tool and an online dictionary are used to identify the language and to translate the documents to be used in cross-lingual similarity algorithms.