Advances Towards Semantic Plagiarism Detection
Hassan Issa, Katja Hose, Steffen Metzger, Ralf Schenkel · 2011
Recent events have again shown that plagiarism detection is an important problem in today’s so-ciety. The flood of documents, however, makes detection more and more difficult so that the ap-plication of computer-based methods is a natural consequence. The application of text comparison techniques, however, eventually leads to ‘intel-ligent ’ plagiarism, where sentences are slightly rephrased or synonyms are used. To help detect-ing such plagiarism, we propose to use seman-tic similarity between documents based on infor-mation extracting techniques. This notion is also useful for other applications such as finding sim-ilar news articles and research papers. 1