Monolingual plagiarism detection is a challenging and underexplored area in Natural Language Processing (NLP). Existing systems lack accuracy due to their limited consideration of semantics, Named Entity Recognition (NER), and paraphrases. The proposed research aims to overcome the limitations of existing approaches by creating a new system for MonoLingual Plagiarism Detection (MLPD). The system utilizes Semantic Analysis and advanced methods to accurately check text similarity between Hindi-English language pairs, addressing the challenges of Monolingual plagiarism. Monolingual plagiarism detection addresses the challenges by employing semantic analysis, NER identification, and paraphrase detection. Leveraging semantic algorithms like WordNet, LSA, and BERT, the system captures underlying meaning and detects similarities across languages. NER recognition enhances detection by identifying named entities, while paraphrase detection identifies equivalent expressions. The outcomes of this research contribute to the advancement of plagiarism detection systems, promoting integrity in a monolingual world. leveraging semantic analysis algorithms proved to be out performed in achieving accurate and efficient plagiarism percentage.

Monolingual plagiarism detection, Semantic Analysis, LSA, WordNet, BERT Algorithm, Text Similarity, Named Entity Recognition