Cross-Language Plagiarism Detection Methods

The present paper provides a summary on the existing approaches to plagiarism detection in multilingual context. Our aim is to organize the available data for the further research. Considering distant language pairs is of a particular interest for us. Cross-language plagiarism detection issue has acquired pronounced importance lately, since semantic contents of a document can be easily and discreetly plagiarized through the use of translation (human or machine-based). We attempt to show the development of detection approaches from the first experiments based on machine translation pre-processing to the up-to-date knowledge-based systems that proved to obtain reliable results on various corpora.