This paper describes the cross-language plagiarism detection method CLAD (Cross-Language Analog Detector) between test document and indexed documents. The main difference of this method from existing versions is the detection of plagiarism among multiple languages not only two languages. While translating terms, it used the dictionary-based machine-translation method. CLAD’s working process consists of document indexing and detection process phases. In this paper, we will describe both of these phases.
Comparison of Collocation Extraction Measures for Document Indexing