Cross-language plagiarism detection based on WordNet

In this paper, we propose a Cross-language Plagiarism Detection (CLPD) methodology based on the WordNet with the summary and analysis of current researches on both the monolingual and cross-linguistic plagiarism detection. Firstly, we build a language-independent semantic mid-layer based on the nouns of WordNet, and implement a semantic hash encoding on that mid-layer. Secondly, we propose a novel approach for nouns' sense disambiguation based on concept correlation, which is applied in the process of obtaining feature sequences of texts. Through analyzing and comparing the results of experiments, it can be concluded that the methodology is indeed effective.