Investigating Advanced Techniques for Document Content Similarity Applied to External Plagiarism Analysis

We present an approach to perform external plagiarism analysis by applying several similarity detection techniques, such as lexical measures and a textual entailment recognition system developed by our research group. Some of the least expensive features of this system are applied to all corpus documents to detect those that are likely to be plagiarized. After this is done, the whole system is applied over this subset of documents to extract the exact n-grams that have been plagiarized, given that we now have less data to process and therefore can use a more complex and costly function. Apart from the application of strictly lexical measures, we also experiment with a textual entailment recognition system to detect plagiarisms with a high level of obfuscation. In addition, we experiment with the application of a spell corrector and a machine translation system to handle misspellings and plagiarisms translated into different languages, respectively.