T-SRE: Transformer-based semantic Relation extraction for contextual paraphrased plagiarism detection

Plagiarism has become a pervasive issue in academics and professionals to safeguard academic integrity and intellectual property rights. The escalating sophistication of plagiarized content through semantic manipulation and structural reorganization poses significant challenges to existing detection systems that rely primarily on lexical similarity measures. The proposed T-SRE (Transformer-based Semantic Relation Extraction), a novel framework addresses the limitations of traditional n-gram and string-matching approaches by leveraging deep semantic analysis. The proposed framework combines Dependency Parsing (DP) for syntactic relationship mapping and Named Entity Recognition (NER) for contextual entity identification, augmented by a transformer-based neural network that captures long-range contextual dependencies. This learning methodology incorporates three key components: a position-aware word reordering algorithm, Levenshtein distance metric for structural similarity, and contextual word embeddings for semantic preservation detection. The proposed T-SRE enhances text structure recognition by combining position-aware reordering with semantic preservation through ensemble learning. The system implements a hierarchical classification scheme that quantifies plagiarism severity through a four-tier taxonomy: heavy, low, non-plagiarized and verbatim copy. The Udacity benchmark dataset showcases the model’s superior detection capabilities, achieving 92% precision, 89% recall, and an F1-score of 90.5%, particularly in lightweight textual modifications.The framework achieves a granularity score of 1.28, outperforming existing approaches.