396e3d57186c1f28fcb4b44 20230720052823063 beie:beie director@blueeyesintelligence.org WEB-FORM International Journal of Recent Technology and Engineering (IJRTE) IJRTE 22773878 10.35940/ijrte.2277-3878 https://www.ijrte.org/ 07 30 2023 12 2 Department of Computer Science Engineering, Abdul Kalam Technical University, Agra (U.P), India. Anshika Singh https://orcid.org/0009-0004-4067-2976 Ankit Garg Department of Computer Science Engineering, Abdul Kalam Technical University, Agra (U.P), India. Scientific publications are essential sources of information for researchers across various fields. However, the increasing number of publications has made it challenging for researchers to keep up with the latest advancements. The task of extracting key phrases and relationships from scientific papers is of utmost importance in the field of natural language processing. This task plays a crucial role in helping researchers efficiently identify relevant articles and extract valuable insights from them. This research focuses on the problem of key phrase extraction, classification, and relationship identification in scientific publications. The problem is divided into two sub-problems: key phrase extraction and classification into PROCESS, TASK, and MATERIAL categories, and relationship identification. To address these sub-problems, advanced technologies such as SciBERT, MiniLM Sentence Transformer, and SVM are utilized. These techniques enable efficient processing and analysis of scientific text, facilitating key phrase extraction, and classification, and relationship identification. By effectively tackling these challenges, researchers can navigate the vast amount of scientific literature more efficiently, identifying relevant articles, and uncovering valuable connections and insights within the text. 07 30 2023 110 113 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true International Journal of Recent Technology and Engineering (IJRTE) No, I did not receive any financial support for this article. No conflicts of interest to the best of our knowledge. No, this article does not require ethical approval and consent to participate with evidence. Not relevant. Anshika Singh actively participated in the research process and made significant contributions to the manuscript. She played a role in the study conception and design, conducted literature search and categorization, and developed the machine learning models. Anshika wrote sections related to data preprocessing, experimental methodology, and evaluation. Ankit Garg provided supervision for the research and offered critical feedback on the manuscript. His guidance and support were instrumental in shaping the direction of the study. Ankit's expertise and input helped refine the research methodology and strengthen the overall findings. 10.35940/ijrte.B7846.0712223 https://www.ijrte.org/portfolio-item/B78460712223/