DETERMINING SEMANTIC SIMILARITY AND INCREASING THE EFFICIENCY OF ANTIPLAGIAT SYSTEMS BASED ON ARTIFICIAL INTELLIGENCE

Authors

  • Elyor Khayitmamatovich Egamberdiev Tashkent University of Information Technologies named after Muhammad al-Khwarizmi

Keywords:

semantic anti-plagiarism, artificial intelligence, natural language processing, NLP, Transformer, BERT, Sentence-BERT, embedding, cosine similarity, semantic distance, academic integrity, plagiarism detection

Abstract

This article examines modern development trends in semantic anti-plagiarism systems, natural language processing (NLP) methods, and the possibilities of using embedding models based on the Transformer architecture. The study utilized indicators of cosine similarity and semantic distance to identify hidden semantic connections between texts. The proposed approach demonstrates high accuracy compared to traditional anti-plagiarism systems.

Downloads

Published

2026-06-14

Issue

No. 6 (2026): Innovations in Science, Technology, and Holistic Education

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.