Evaluation of Text Reuse Corpora for Text Alignment Task of plagiarism Detection Notebook for PAN at CLEF 2015
Vahid Zarrabi, Javad Rafiei, Khadijeh Khoshnava, Habibollah Asghari, Salar Mohtaj · 2015
This paper addresses the text alignment task of 7th International competition on plagiarism detection; PAN 2015. We investigate five submitted corpora and evaluate them based on their characteristics in two ways: manual and automatic evaluation. The results of evaluation show that the most of pla- giarism cases in prepared corporahavea rather high quality in term of rate of obfuscation alongside preserving the concepts.