Towards the 2nd International Competition on Plagiarism Detection and Beyond

Abstract

Multiple tools that assist in the detection of text plagiarism (known as automatic plagiarism detectors) have been developed in recent years. However, there is still an unanswered question: Which plagiarism detection method performs best? Due to the lack of a standard evaluation framework for plagiarism detection, providing an answer to this question is still not possible nowadays. As a response, the International Competition on Plagiarism Detection has been created (Potthast et al., 2009). In this paper an overview of the results of the first competition is provided. A description of how the second edition is being developed and its perspectives are also included. By having a competition on plagiarism detection, where different models can be objectively compared, the response to the previous question is getting closer. Additionally, an overview of what we believe to be missing from automatic plagiarism detection—cross-language plagiarism—is provided. 1