CIVILICA We Respect the Science
(ناشر تخصصی کنفرانسهای کشور / شماره مجوز انتشارات از وزارت فرهنگ و ارشاد اسلامی: ۸۹۷۱)

Multilingual Idea plagiarism detection for scientific text based on Word Net Dataset

عنوان مقاله: Multilingual Idea plagiarism detection for scientific text based on Word Net Dataset
شناسه ملی مقاله: NPECE01_090
منتشر شده در اولین کنفرانس بین المللی چشم انداز های نو در مهندسی برق و کامپیوتر در سال 1395
مشخصات نویسندگان مقاله:

Elnaz Asgarifar - Department of Computer and Information Technology Engineering, Qazvin Branch,Islamic Azad University, Qazvin, Iran
Azam Bastanfard - Department of Mechatronic, Karaj Branch,Islamic Azad University, Karaj, Iran

خلاصه مقاله:
Plagiarism occurs when the content is copied without any permission or citation. By increasing the scientific text, the plagiarism in this domain has been increased. This paper introduced the plagiarism detection method that recognized the plagiarism based on WordNet dataset in thirty-four different languages. In a scientific text, the proposed method works locally and used bag of words file. In this case the processing time can be improved. In addition, acceptable precision, recall and f-measure value in provided method has been showed by experimental results on PAN2014 and open multilingual WordNet dataset for thirty-four languages. So it can be suggested for scientific text and it is not limited by one language.

کلمات کلیدی:
plagiarism detection, open multilingual WordNet dataset, bag of words file

صفحه اختصاصی مقاله و دریافت فایل کامل: https://civilica.com/doc/555432/