Identification of Plagiarism Using Syntactic and Semantic Filters

We present a work on detection of manual paraphrasing in documents in comparison with a set of source documents. Manual paraphrasing is a realistic type of plagiarism, where the obfuscation is introduced manually in documents. We have used PAN-PC-10 data set to develop and evaluate our algorithm. The proposed approach consists of two steps, namely, identification of probable plagiarized passages using dice similarity measure and filtering the obtained passages using syntactic rules and lexical semantic features extracted from obfuscation patterns. The algorithm works at sentence level. The results are encouraging in difficult cases of plagiarism that most of the existing approaches fail to detect.