基于多特征的跨语言剽窃检测技术研究

Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-10-11 Cooperative journals: 《计算机应用研究》

刘刚 胡昱临 李光曦

Abstract： In order to solve the problem of bilingual plagiarism, this paper constructed a multi-feature-based cross-language plagiarism detection model. This paper firstly analyzes and summarizes the research status of single and double language plagiarism, and proposes a multi-feature-based cross-language plagiarism detection model. The model includes multi-feature-selection-based cross-language plagiarism classification and multi-feature-correspondence–based cross-language plagiarism detection. The results of plagiarism filtering two times is mainly based on the correspondence between translation features and structural features. Finally, the last plagiarism is confirmed by WordNet. In this paper, the transcendental plagiarism model is established, and the results of the classification and the test results are verified by experimental comparison and experimental analysis. The validity and scientificity of the model are proved.

 Hits 1622  Downloads 978  Comment